Datasets:

librarian-bots

/

model_cards_with_metadata_test

like 1

Follow

Librarian Bots 57

akdeniz27/bert-base-turkish-cased-ner

akdeniz27

transformers

token-classification

--- language: tr license: mit widget: - text: "Mustafa Kemal Atatürk 19 Mayıs 1919'da Samsun'a çıktı." --- # Turkish Named Entity Recognition (NER) Model This model is the fine-tuned model of "dbmdz/bert-base-turkish-cased" using a reviewed version of well known Turkish NER dataset (https://github.com/stefan-it/turkish-bert/files/4558187/nerdata.txt). # Fine-tuning parameters: ``` task = "ner" model_checkpoint = "dbmdz/bert-base-turkish-cased" batch_size = 8 label_list = ['O', 'B-PER', 'I-PER', 'B-ORG', 'I-ORG', 'B-LOC', 'I-LOC'] max_length = 512 learning_rate = 2e-5 num_train_epochs = 3 weight_decay = 0.01 ``` # How to use: ``` model = AutoModelForTokenClassification.from_pretrained("akdeniz27/bert-base-turkish-cased-ner") tokenizer = AutoTokenizer.from_pretrained("akdeniz27/bert-base-turkish-cased-ner") ner = pipeline('ner', model=model, tokenizer=tokenizer, aggregation_strategy="first") ner("your text here") ``` Pls refer "https://huggingface.co/transformers/_modules/transformers/pipelines/token_classification.html" for entity grouping with aggregation_strategy parameter. # Reference test results: * accuracy: 0.9933935699477056 * f1: 0.9592969472710453 * precision: 0.9543530277931161 * recall: 0.9642923563325274 Evaluation results with the test sets proposed in ["Küçük, D., Küçük, D., Arıcı, N. 2016. Türkçe Varlık İsmi Tanıma için bir Veri Kümesi ("A Named Entity Recognition Dataset for Turkish"). IEEE Sinyal İşleme, İletişim ve Uygulamaları Kurultayı. Zonguldak, Türkiye."](https://ieeexplore.ieee.org/document/7495744) paper. * Test Set Acc. Prec. Rec. F1-Score * 20010000 0.9946 0.9871 0.9463 0.9662 * 20020000 0.9928 0.9134 0.9206 0.9170 * 20030000 0.9942 0.9814 0.9186 0.9489 * 20040000 0.9943 0.9660 0.9522 0.9590 * 20050000 0.9971 0.9539 0.9932 0.9732 * 20060000 0.9993 0.9942 0.9942 0.9942 * 20070000 0.9970 0.9806 0.9439 0.9619 * 20080000 0.9988 0.9821 0.9649 0.9735 * 20090000 0.9977 0.9891 0.9479 0.9681 * 20100000 0.9961 0.9684 0.9293 0.9485 * Overall 0.9961 0.9720 0.9516 0.9617

facebook/dinov2-large

facebook

transformers

image-feature-extraction

--- license: apache-2.0 tags: - dino - vision --- # Vision Transformer (large-sized model) trained using DINOv2 Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper [DINOv2: Learning Robust Visual Features without Supervision](https://arxiv.org/abs/2304.07193) by Oquab et al. and first released in [this repository](https://github.com/facebookresearch/dinov2). Disclaimer: The team releasing DINOv2 did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion. Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One also adds absolute position embeddings before feeding the sequence to the layers of the Transformer encoder. Note that this model does not include any fine-tuned heads. By pre-training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled images for instance, you can train a standard classifier by placing a linear layer on top of the pre-trained encoder. One typically places a linear layer on top of the [CLS] token, as the last hidden state of this token can be seen as a representation of an entire image. ## Intended uses & limitations You can use the raw model for feature extraction. See the [model hub](https://huggingface.co/models?search=facebook/dinov2) to look for fine-tuned versions on a task that interests you. ### How to use Here is how to use this model: ```python from transformers import AutoImageProcessor, AutoModel from PIL import Image import requests url = 'http://images.cocodataset.org/val2017/000000039769.jpg' image = Image.open(requests.get(url, stream=True).raw) processor = AutoImageProcessor.from_pretrained('facebook/dinov2-large') model = AutoModel.from_pretrained('facebook/dinov2-large') inputs = processor(images=image, return_tensors="pt") outputs = model(**inputs) last_hidden_states = outputs.last_hidden_state ``` ### BibTeX entry and citation info ```bibtex misc{oquab2023dinov2, title={DINOv2: Learning Robust Visual Features without Supervision}, author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski}, year={2023}, eprint={2304.07193}, archivePrefix={arXiv}, primaryClass={cs.CV} } ```

facebook/mask2former-swin-base-coco-panoptic

facebook

transformers

image-segmentation

--- license: other tags: - vision - image-segmentation datasets: - coco widget: - src: http://images.cocodataset.org/val2017/000000039769.jpg example_title: Cats - src: http://images.cocodataset.org/val2017/000000039770.jpg example_title: Castle --- # Mask2Former Mask2Former model trained on COCO panoptic segmentation (base-sized version, Swin backbone). It was introduced in the paper [Masked-attention Mask Transformer for Universal Image Segmentation ](https://arxiv.org/abs/2112.01527) and first released in [this repository](https://github.com/facebookresearch/Mask2Former/). Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, [MaskFormer](https://arxiv.org/abs/2107.06278) both in terms of performance an efficiency by (i) replacing the pixel decoder with a more advanced multi-scale deformable attention Transformer, (ii) adopting a Transformer decoder with masked attention to boost performance without without introducing additional computation and (iii) improving training efficiency by calculating the loss on subsampled points instead of whole masks.  ## Intended uses & limitations You can use this particular checkpoint for panoptic segmentation. See the [model hub](https://huggingface.co/models?search=mask2former) to look for other fine-tuned versions on a task that interests you. ### How to use Here is how to use this model: ```python import requests import torch from PIL import Image from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation # load Mask2Former fine-tuned on COCO panoptic segmentation processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-base-coco-panoptic") model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-base-coco-panoptic") url = "http://images.cocodataset.org/val2017/000000039769.jpg" image = Image.open(requests.get(url, stream=True).raw) inputs = processor(images=image, return_tensors="pt") with torch.no_grad(): outputs = model(**inputs) # model predicts class_queries_logits of shape `(batch_size, num_queries)` # and masks_queries_logits of shape `(batch_size, num_queries, height, width)` class_queries_logits = outputs.class_queries_logits masks_queries_logits = outputs.masks_queries_logits # you can pass them to processor for postprocessing result = processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0] # we refer to the demo notebooks for visualization (see "Resources" section in the Mask2Former docs) predicted_panoptic_map = result["segmentation"] ``` For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/mask2former).

mistralai/Mistral-7B-v0.1

mistralai

transformers

text-generation

--- license: apache-2.0 pipeline_tag: text-generation language: - en tags: - pretrained inference: parameters: temperature: 0.7 --- # Model Card for Mistral-7B-v0.1 The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested. For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/announcing-mistral-7b/). ## Model Architecture Mistral-7B-v0.1 is a transformer model, with the following architecture choices: - Grouped-Query Attention - Sliding-Window Attention - Byte-fallback BPE tokenizer ## Troubleshooting - If you see the following error: ``` KeyError: 'mistral' ``` - Or: ``` NotImplementedError: Cannot copy out of meta tensor; no data! ``` Ensure you are utilizing a stable version of Transformers, 4.34.0 or newer. ## Notice Mistral 7B is a pretrained base model and therefore does not have any moderation mechanisms. ## The Mistral AI Team Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.

facebook/detr-resnet-101

facebook

transformers

object-detection

--- license: apache-2.0 tags: - object-detection - vision datasets: - coco widget: - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg example_title: Savanna - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg example_title: Football Match - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg example_title: Airport --- # DETR (End-to-End Object Detection) model with ResNet-101 backbone DEtection TRansformer (DETR) model trained end-to-end on COCO 2017 object detection (118k annotated images). It was introduced in the paper [End-to-End Object Detection with Transformers](https://arxiv.org/abs/2005.12872) by Carion et al. and first released in [this repository](https://github.com/facebookresearch/detr). Disclaimer: The team releasing DETR did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description The DETR model is an encoder-decoder transformer with a convolutional backbone. Two heads are added on top of the decoder outputs in order to perform object detection: a linear layer for the class labels and a MLP (multi-layer perceptron) for the bounding boxes. The model uses so-called object queries to detect objects in an image. Each object query looks for a particular object in the image. For COCO, the number of object queries is set to 100. The model is trained using a "bipartite matching loss": one compares the predicted classes + bounding boxes of each of the N = 100 object queries to the ground truth annotations, padded up to the same length N (so if an image only contains 4 objects, 96 annotations will just have a "no object" as class and "no bounding box" as bounding box). The Hungarian matching algorithm is used to create an optimal one-to-one mapping between each of the N queries and each of the N annotations. Next, standard cross-entropy (for the classes) and a linear combination of the L1 and generalized IoU loss (for the bounding boxes) are used to optimize the parameters of the model.  ## Intended uses & limitations You can use the raw model for object detection. See the [model hub](https://huggingface.co/models?search=facebook/detr) to look for all available DETR models. ### How to use Here is how to use this model: ```python from transformers import DetrImageProcessor, DetrForObjectDetection import torch from PIL import Image import requests url = "http://images.cocodataset.org/val2017/000000039769.jpg" image = Image.open(requests.get(url, stream=True).raw) # you can specify the revision tag if you don't want the timm dependency processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-101", revision="no_timm") model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-101", revision="no_timm") inputs = processor(images=image, return_tensors="pt") outputs = model(**inputs) # convert outputs (bounding boxes and class logits) to COCO API # let's only keep detections with score > 0.9 target_sizes = torch.tensor([image.size[::-1]]) results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0] for score, label, box in zip(results["scores"], results["labels"], results["boxes"]): box = [round(i, 2) for i in box.tolist()] print( f"Detected {model.config.id2label[label.item()]} with confidence " f"{round(score.item(), 3)} at location {box}" ) ``` This should output (something along the lines of): ``` Detected cat with confidence 0.998 at location [344.06, 24.85, 640.34, 373.74] Detected remote with confidence 0.997 at location [328.13, 75.93, 372.81, 187.66] Detected remote with confidence 0.997 at location [39.34, 70.13, 175.56, 118.78] Detected cat with confidence 0.998 at location [15.36, 51.75, 316.89, 471.16] Detected couch with confidence 0.995 at location [-0.19, 0.71, 639.73, 474.17] ``` Currently, both the feature extractor and model support PyTorch. ## Training data The DETR model was trained on [COCO 2017 object detection](https://cocodataset.org/#download), a dataset consisting of 118k/5k annotated images for training/validation respectively. ## Training procedure ### Preprocessing The exact details of preprocessing of images during training/validation can be found [here](https://github.com/google-research/vision_transformer/blob/master/vit_jax/input_pipeline.py). Images are resized/rescaled such that the shortest side is at least 800 pixels and the largest side at most 1333 pixels, and normalized across the RGB channels with the ImageNet mean (0.485, 0.456, 0.406) and standard deviation (0.229, 0.224, 0.225). ### Training The model was trained for 300 epochs on 16 V100 GPUs. This takes 3 days, with 4 images per GPU (hence a total batch size of 64). ## Evaluation results This model achieves an AP (average precision) of **43.5** on COCO 2017 validation. For more details regarding evaluation results, we refer to table 1 of the original paper. ### BibTeX entry and citation info ```bibtex @article{DBLP:journals/corr/abs-2005-12872, author = {Nicolas Carion and Francisco Massa and Gabriel Synnaeve and Nicolas Usunier and Alexander Kirillov and Sergey Zagoruyko}, title = {End-to-End Object Detection with Transformers}, journal = {CoRR}, volume = {abs/2005.12872}, year = {2020}, url = {https://arxiv.org/abs/2005.12872}, archivePrefix = {arXiv}, eprint = {2005.12872}, timestamp = {Thu, 28 May 2020 17:38:09 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2005-12872.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ```

TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ

TheBloke

transformers

text-generation

--- base_model: mistralai/Mixtral-8x7B-Instruct-v0.1 inference: false language: - fr - it - de - es - en license: apache-2.0 model_creator: Mistral AI_ model_name: Mixtral 8X7B Instruct v0.1 model_type: mixtral prompt_template: '[INST] {prompt} [/INST] ' quantized_by: TheBloke widget: - output: text: 'Arr, shiver me timbers! Ye have a llama on yer lawn, ye say? Well, that be a new one for me! Here''s what I''d suggest, arr: 1. Firstly, ensure yer safety. Llamas may look gentle, but they can be protective if they feel threatened. 2. Try to make the area less appealing to the llama. Remove any food sources or water that might be attracting it. 3. Contact local animal control or a wildlife rescue organization. They be the experts and can provide humane ways to remove the llama from yer property. 4. If ye have any experience with animals, you could try to gently herd the llama towards a nearby field or open space. But be careful, arr! Remember, arr, it be important to treat the llama with respect and care. It be a creature just trying to survive, like the rest of us.' text: '[INST] You are a pirate chatbot who always responds with Arr and pirate speak! There''s a llama on my lawn, how can I get rid of him? [/INST]' --- <!-- markdownlint-disable MD041 --> <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Mixtral 8X7B Instruct v0.1 - GPTQ - Model creator: [Mistral AI_](https://huggingface.co/mistralai) - Original model: [Mixtral 8X7B Instruct v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) <!-- description start --> # Description This repo contains GPTQ model files for [Mistral AI_'s Mixtral 8X7B Instruct v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1). Mixtral GPTQs currently require: * Transformers 4.36.0 or later * either, AutoGPTQ 0.6 compiled from source, or * Transformers 4.37.0.dev0 compiled from Github with: `pip3 install git+https://github.com/huggingface/transformers` Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them. <!-- description end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF) * [Mistral AI_'s original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: Mistral ``` [INST] {prompt} [/INST] ``` <!-- prompt-template end --> <!-- README_GPTQ.md-compatible clients start --> ## Known compatible clients / servers GPTQ models are currently supported on Linux (NVidia/AMD) and Windows (NVidia only). macOS users: please use GGUF models. Mixtral GPTQs currently have special requirements - see Description above. <!-- README_GPTQ.md-compatible clients end --> <!-- README_GPTQ.md-provided-files start --> ## Provided files, and GPTQ parameters Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements. Each separate quant is in a different branch. See below for instructions on fetching from different branches. Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers. <details> <summary>Explanation of GPTQ parameters</summary> - Bits: The bit size of the quantised model. - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value. - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now. - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy. - GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s). - Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences. - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit. </details> | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc | | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- | | [main](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 23.81 GB | No | 4-bit, with Act Order. No group size, to lower VRAM requirements. | | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 24.70 GB | No | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. | | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 27.42 GB | No | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. | | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 18.01 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. | | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 18.85 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. | | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 47.04 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. | | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 48.10 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. | <!-- README_GPTQ.md-provided-files end --> <!-- README_GPTQ.md-download-from-branches start --> ## How to download, including from branches ### In text-generation-webui To download from the `main` branch, enter `TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ` in the "Download model" box. To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ:gptq-4bit-128g-actorder_True` ### From the command line I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` To download the `main` branch to a folder called `Mixtral-8x7B-Instruct-v0.1-GPTQ`: ```shell mkdir Mixtral-8x7B-Instruct-v0.1-GPTQ huggingface-cli download TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ --local-dir Mixtral-8x7B-Instruct-v0.1-GPTQ --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: ```shell mkdir Mixtral-8x7B-Instruct-v0.1-GPTQ huggingface-cli download TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ --revision gptq-4bit-128g-actorder_True --local-dir Mixtral-8x7B-Instruct-v0.1-GPTQ --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model. The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`. For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell mkdir Mixtral-8x7B-Instruct-v0.1-GPTQ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ --local-dir Mixtral-8x7B-Instruct-v0.1-GPTQ --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> ### With `git` (**not** recommended) To clone a specific branch with `git`, use a command like this: ```shell git clone --single-branch --branch gptq-4bit-128g-actorder_True https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ ``` Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.) <!-- README_GPTQ.md-download-from-branches end --> <!-- README_GPTQ.md-text-generation-webui start --> ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui) **NOTE**: Requires: * Transformers 4.36.0, or Transformers 4.37.0.dev0 from Github * Either AutoGPTQ 0.6 compiled from source and `Loader: AutoGPTQ`, * or, `Loader: Transformers`, if you installed Transformers from Github: `pip3 install git+https://github.com/huggingface/transformers` Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui). It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install. 1. Click the **Model tab**. 2. Under **Download custom model or LoRA**, enter `TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ`. - To download from a specific branch, enter for example `TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ:gptq-4bit-128g-actorder_True` - see Provided Files above for the list of branches for each option. 3. Click **Download**. 4. The model will start downloading. Once it's finished it will say "Done". 5. In the top left, click the refresh icon next to **Model**. 6. In the **Model** dropdown, choose the model you just downloaded: `Mixtral-8x7B-Instruct-v0.1-GPTQ` 7. The model will automatically load, and is now ready for use! 8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right. - Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`. 9. Once you're ready, click the **Text Generation** tab and enter a prompt to get started! <!-- README_GPTQ.md-text-generation-webui end --> <!-- README_GPTQ.md-use-from-tgi start --> ## Serving this model from Text Generation Inference (TGI) Not currently supported for Mixtral models. <!-- README_GPTQ.md-use-from-tgi end --> <!-- README_GPTQ.md-use-from-python start --> ## Python code example: inference from this GPTQ model ### Install the necessary packages Requires: Transformers 4.37.0.dev0 from Github, Optimum 1.16.0 or later, and AutoGPTQ 0.5.1 or later. ```shell pip3 install --upgrade "git+https://github.com/huggingface/transformers" optimum # If using PyTorch 2.1 + CUDA 12.x: pip3 install --upgrade auto-gptq # or, if using PyTorch 2.1 + CUDA 11.x: pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ ``` If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source: ```shell pip3 uninstall -y auto-gptq git clone https://github.com/PanQiWei/AutoGPTQ cd AutoGPTQ DISABLE_QIGEN=1 pip3 install . ``` ### Example Python code ```python from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline model_name_or_path = "TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ" # To use a different branch, change revision # For example: revision="gptq-4bit-128g-actorder_True" model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=False, revision="main") tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) prompt = "Write a story about llamas" system_message = "You are a story writing assistant" prompt_template=f'''[INST] {prompt} [/INST] ''' print("\n\n*** Generate:") input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda() output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512) print(tokenizer.decode(output[0])) # Inference can also be done using transformers' pipeline print("*** Pipeline:") pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1 ) print(pipe(prompt_template)[0]['generated_text']) ``` <!-- README_GPTQ.md-use-from-python end --> <!-- README_GPTQ.md-compatibility start --> ## Compatibility The files provided are tested to work with AutoGPTQ 0.6 (compiled from source) and Transformers 4.37.0 (installed from Github). <!-- README_GPTQ.md-compatibility end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Aemon Algiz. **Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> # Original model card: Mistral AI_'s Mixtral 8X7B Instruct v0.1 # Model Card for Mixtral-8x7B The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested. For full details of this model please read our [release blog post](https://mistral.ai/news/mixtral-of-experts/). ## Warning This repo contains weights that are compatible with [vLLM](https://github.com/vllm-project/vllm) serving of the model as well as Hugging Face [transformers](https://github.com/huggingface/transformers) library. It is based on the original Mixtral [torrent release](magnet:?xt=urn:btih:5546272da9065eddeb6fcd7ffddeef5b75be79a7&dn=mixtral-8x7b-32kseqlen&tr=udp%3A%2F%http://2Fopentracker.i2p.rocks%3A6969%2Fannounce&tr=http%3A%2F%http://2Ftracker.openbittorrent.com%3A80%2Fannounce), but the file format and parameter names are different. Please note that model cannot (yet) be instantiated with HF. ## Instruction format This format must be strictly respected, otherwise the model will generate sub-optimal outputs. The template used to build a prompt for the Instruct model is defined as follows: ``` <s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST] ``` Note that `<s>` and `</s>` are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings. As reference, here is the pseudo-code used to tokenize instructions during fine-tuning: ```python def tokenize(text): return tok.encode(text, add_special_tokens=False) [BOS_ID] + tokenize("[INST]") + tokenize(USER_MESSAGE_1) + tokenize("[/INST]") + tokenize(BOT_MESSAGE_1) + [EOS_ID] + … tokenize("[INST]") + tokenize(USER_MESSAGE_N) + tokenize("[/INST]") + tokenize(BOT_MESSAGE_N) + [EOS_ID] ``` In the pseudo-code above, note that the `tokenize` method should not add a BOS or EOS token automatically, but should add a prefix space. ## Run the model ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id) text = "Hello my name is" inputs = tokenizer(text, return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` By default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem: ### In half-precision Note `float16` precision only works on GPU devices <details> <summary> Click to expand </summary> ```diff + import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) + model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16).to(0) text = "Hello my name is" + inputs = tokenizer(text, return_tensors="pt").to(0) outputs = model.generate(**inputs, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` </details> ### Lower precision using (8-bit & 4-bit) using `bitsandbytes` <details> <summary> Click to expand </summary> ```diff + import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) + model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True) text = "Hello my name is" + inputs = tokenizer(text, return_tensors="pt").to(0) outputs = model.generate(**inputs, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` </details> ### Load the model with Flash Attention 2 <details> <summary> Click to expand </summary> ```diff + import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) + model = AutoModelForCausalLM.from_pretrained(model_id, use_flash_attention_2=True) text = "Hello my name is" + inputs = tokenizer(text, return_tensors="pt").to(0) outputs = model.generate(**inputs, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` </details> ## Limitations The Mixtral-8x7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs. # The Mistral AI Team Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.

lmsys/fastchat-t5-3b-v1.0

lmsys

transformers

text2text-generation

--- license: apache-2.0 inference: false --- # FastChat-T5 Model Card ## Model details **Model type:** FastChat-T5 is an open-source chatbot trained by fine-tuning Flan-t5-xl (3B parameters) on user-shared conversations collected from ShareGPT. It is based on an encoder-decoder transformer architecture, and can autoregressively generate responses to users' inputs. **Model date:** FastChat-T5 was trained on April 2023. **Organizations developing the model:** The FastChat developers, primarily Dacheng Li, Lianmin Zheng and Hao Zhang. **Paper or resources for more information:** https://github.com/lm-sys/FastChat#FastChat-T5 **License:** Apache License 2.0 **Where to send questions or comments about the model:** https://github.com/lm-sys/FastChat/issues ## Intended use **Primary intended uses:** The primary use of FastChat-T5 is the commercial usage of large language models and chatbots. It can also be used for research purposes. **Primary intended users:** The primary intended users of the model are entrepreneurs and researchers in natural language processing, machine learning, and artificial intelligence. ## Training dataset 70K conversations collected from ShareGPT.com. ## Training details It processes the ShareGPT data in the form of question answering. Each ChatGPT response is processed as an answer, and previous conversations between the user and the ChatGPT are processed as the question. The encoder bi-directionally encodes a question into a hidden representation. The decoder uses cross-attention to attend to this representation while generating an answer uni-directionally from a start token. This model is fine-tuned for 3 epochs, with a max learning rate 2e-5, warmup ratio 0.03, and a cosine learning rate schedule. ## Evaluation dataset A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details.

pyannote/speaker-diarization-3.0

pyannote

pyannote-audio

automatic-speech-recognition

--- tags: - pyannote - pyannote-audio - pyannote-audio-pipeline - audio - voice - speech - speaker - speaker-diarization - speaker-change-detection - voice-activity-detection - overlapped-speech-detection - automatic-speech-recognition license: mit extra_gated_prompt: "The collected information will help acquire a better knowledge of pyannote.audio userbase and help its maintainers improve it further. Though this pipeline uses MIT license and will always remain open-source, we will occasionnally email you about premium pipelines and paid services around pyannote." extra_gated_fields: Company/university: text Website: text --- Using this open-source model in production? Consider switching to [pyannoteAI](https://www.pyannote.ai) for better and faster options. # 🎹 Speaker diarization 3.0 This pipeline has been trained by Séverin Baroudi with [pyannote.audio](https://github.com/pyannote/pyannote-audio) `3.0.0` using a combination of the training sets of AISHELL, AliMeeting, AMI, AVA-AVD, DIHARD, Ego4D, MSDWild, REPERE, and VoxConverse. It ingests mono audio sampled at 16kHz and outputs speaker diarization as an [`Annotation`](http://pyannote.github.io/pyannote-core/structure.html#annotation) instance: * stereo or multi-channel audio files are automatically downmixed to mono by averaging the channels. * audio files sampled at a different rate are resampled to 16kHz automatically upon loading. ## Requirements 1. Install [`pyannote.audio`](https://github.com/pyannote/pyannote-audio) `3.0` with `pip install pyannote.audio` 2. Accept [`pyannote/segmentation-3.0`](https://hf.co/pyannote/segmentation-3.0) user conditions 3. Accept [`pyannote/speaker-diarization-3.0`](https://hf.co/pyannote-speaker-diarization-3.0) user conditions 4. Create access token at [`hf.co/settings/tokens`](https://hf.co/settings/tokens). ## Usage ```python # instantiate the pipeline from pyannote.audio import Pipeline pipeline = Pipeline.from_pretrained( "pyannote/speaker-diarization-3.0", use_auth_token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE") # run the pipeline on an audio file diarization = pipeline("audio.wav") # dump the diarization output to disk using RTTM format with open("audio.rttm", "w") as rttm: diarization.write_rttm(rttm) ``` ### Processing on GPU `pyannote.audio` pipelines run on CPU by default. You can send them to GPU with the following lines: ```python import torch pipeline.to(torch.device("cuda")) ``` Real-time factor is around 2.5% using one Nvidia Tesla V100 SXM2 GPU (for the neural inference part) and one Intel Cascade Lake 6248 CPU (for the clustering part). In other words, it takes approximately 1.5 minutes to process a one hour conversation. ### Processing from memory Pre-loading audio files in memory may result in faster processing: ```python waveform, sample_rate = torchaudio.load("audio.wav") diarization = pipeline({"waveform": waveform, "sample_rate": sample_rate}) ``` ### Monitoring progress Hooks are available to monitor the progress of the pipeline: ```python from pyannote.audio.pipelines.utils.hook import ProgressHook with ProgressHook() as hook: diarization = pipeline("audio.wav", hook=hook) ``` ### Controlling the number of speakers In case the number of speakers is known in advance, one can use the `num_speakers` option: ```python diarization = pipeline("audio.wav", num_speakers=2) ``` One can also provide lower and/or upper bounds on the number of speakers using `min_speakers` and `max_speakers` options: ```python diarization = pipeline("audio.wav", min_speakers=2, max_speakers=5) ``` ## Benchmark This pipeline has been benchmarked on a large collection of datasets. Processing is fully automatic: * no manual voice activity detection (as is sometimes the case in the literature) * no manual number of speakers (though it is possible to provide it to the pipeline) * no fine-tuning of the internal models nor tuning of the pipeline hyper-parameters to each dataset ... with the least forgiving diarization error rate (DER) setup (named *"Full"* in [this paper](https://doi.org/10.1016/j.csl.2021.101254)): * no forgiveness collar * evaluation of overlapped speech | Benchmark | [DER%](. "Diarization error rate") | [FA%](. "False alarm rate") | [Miss%](. "Missed detection rate") | [Conf%](. "Speaker confusion rate") | Expected output | File-level evaluation | | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------- | --------------------------- | ---------------------------------- | ----------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- | | [AISHELL-4](http://www.openslr.org/111/) | 12.3 | 3.8 | 4.4 | 4.1 | [RTTM](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/AISHELL.SpeakerDiarization.Benchmark.test.rttm) | [eval](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/AISHELL.SpeakerDiarization.Benchmark.test.eval) | | [AliMeeting (*channel 1*)](https://www.openslr.org/119/) | 24.3 | 4.4 | 10.0 | 9.9 | [RTTM](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/AliMeeting.SpeakerDiarization.Benchmark.test.rttm) | [eval](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/AliMeeting.SpeakerDiarization.Benchmark.test.eval) | | [AMI (*headset mix,*](https://groups.inf.ed.ac.uk/ami/corpus/) [*only_words*)](https://github.com/BUTSpeechFIT/AMI-diarization-setup) | 19.0 | 3.6 | 9.5 | 5.9 | [RTTM](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/AMI.SpeakerDiarization.Benchmark.test.rttm) | [eval](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/AMI.SpeakerDiarization.Benchmark.test.eval) | | [AMI (*array1, channel 1,*](https://groups.inf.ed.ac.uk/ami/corpus/) [*only_words)*](https://github.com/BUTSpeechFIT/AMI-diarization-setup) | 22.2 | 3.8 | 11.2 | 7.3 | [RTTM](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/AMI-SDM.SpeakerDiarization.Benchmark.test.rttm) | [eval](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/AMI-SDM.SpeakerDiarization.Benchmark.test.eval) | | [AVA-AVD](https://arxiv.org/abs/2111.14448) | 49.1 | 10.8 | 15.7| 22.5 | [RTTM](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/AVA-AVD.SpeakerDiarization.Benchmark.test.rttm) | [eval](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/AVA-AVD.SpeakerDiarization.Benchmark.test.eval) | | [DIHARD 3 (*Full*)](https://arxiv.org/abs/2012.01477) | 21.7 | 6.2 | 8.1 | 7.3 | [RTTM](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/DIHARD.SpeakerDiarization.Benchmark.test.rttm) | [eval](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/DIHARD.SpeakerDiarization.Benchmark.test.eval) | | [MSDWild](https://x-lance.github.io/MSDWILD/) | 24.6 | 5.8 | 8.0 | 10.7 | [RTTM](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/MSDWILD.SpeakerDiarization.Benchmark.test.rttm) | [eval](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/MSDWILD.SpeakerDiarization.Benchmark.test.eval) | | [REPERE (*phase 2*)](https://islrn.org/resources/360-758-359-485-0/) | 7.8 | 1.8 | 2.6 | 3.5 | [RTTM](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/REPERE.SpeakerDiarization.Benchmark.test.rttm) | [eval](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/REPERE.SpeakerDiarization.Benchmark.test.eval) | | [VoxConverse (*v0.3*)](https://github.com/joonson/voxconverse) | 11.3 | 4.1 | 3.4 | 3.8 | [RTTM](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/VoxConverse.SpeakerDiarization.Benchmark.test.rttm) | [eval](https://huggingface.co/pyannote/speaker-diarization-3.0.0/blob/main/reproducible_research/VoxConverse.SpeakerDiarization.Benchmark.test.eval) | ## Citations ```bibtex @inproceedings{Plaquet23, author={Alexis Plaquet and Hervé Bredin}, title={{Powerset multi-class cross entropy loss for neural speaker diarization}}, year=2023, booktitle={Proc. INTERSPEECH 2023}, } ``` ```bibtex @inproceedings{Bredin23, author={Hervé Bredin}, title={{pyannote.audio 2.1 speaker diarization pipeline: principle, benchmark, and recipe}}, year=2023, booktitle={Proc. INTERSPEECH 2023}, } ```

mistralai/Mistral-7B-Instruct-v0.2

mistralai

transformers

text-generation

--- license: apache-2.0 pipeline_tag: text-generation tags: - finetuned inference: true widget: - messages: - role: user content: What is your favorite condiment? --- # Model Card for Mistral-7B-Instruct-v0.2 ### > [!CAUTION] > ⚠️ > The `transformers` tokenizer might give incorrect results as it has not been tested by the Mistral team. To make sure that your encoding and decoding is correct, please use `mistral_common` as shown below: ## Encode and Decode with `mistral_common` ```py from mistral_common.tokens.tokenizers.mistral import MistralTokenizer from mistral_common.protocol.instruct.messages import UserMessage from mistral_common.protocol.instruct.request import ChatCompletionRequest mistral_models_path = "MISTRAL_MODELS_PATH" tokenizer = MistralTokenizer.v1() completion_request = ChatCompletionRequest(messages=[UserMessage(content="Explain Machine Learning to me in a nutshell.")]) tokens = tokenizer.encode_chat_completion(completion_request).tokens ``` ## Inference with `mistral_inference` ```py from mistral_inference.model import Transformer from mistral_inference.generate import generate model = Transformer.from_folder(mistral_models_path) out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id) result = tokenizer.decode(out_tokens[0]) print(result) ``` ## Inference with hugging face `transformers` ```py from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") model.to("cuda") generated_ids = model.generate(tokens, max_new_tokens=1000, do_sample=True) # decode with mistral tokenizer result = tokenizer.decode(generated_ids[0].tolist()) print(result) ``` > [!TIP] > PRs to correct the `transformers` tokenizer so that it gives 1-to-1 the same results as the `mistral_common` reference implementation are very welcome! --- The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2. Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1 - 32k context window (vs 8k context in v0.1) - Rope-theta = 1e6 - No Sliding-Window Attention For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/la-plateforme/). ## Instruction format In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id. E.g. ``` text = "<s>[INST] What is your favourite condiment? [/INST]" "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> " "[INST] Do you have mayonnaise recipes? [/INST]" ``` This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method: ```python from transformers import AutoModelForCausalLM, AutoTokenizer device = "cuda" # the device to load the model onto model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") messages = [ {"role": "user", "content": "What is your favourite condiment?"}, {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"}, {"role": "user", "content": "Do you have mayonnaise recipes?"} ] encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt") model_inputs = encodeds.to(device) model.to(device) generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True) decoded = tokenizer.batch_decode(generated_ids) print(decoded[0]) ``` ## Troubleshooting - If you see the following error: ``` Traceback (most recent call last): File "", line 1, in File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained config, kwargs = AutoConfig.from_pretrained( File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained config_class = CONFIG_MAPPING[config_dict["model_type"]] File "/transformers/models/auto/configuration_auto.py", line 723, in getitem raise KeyError(key) KeyError: 'mistral' ``` Installing transformers from source should solve the issue pip install git+https://github.com/huggingface/transformers This should not be required after transformers-v4.33.4. ## Limitations The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs. ## The Mistral AI Team Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.

WhereIsAI/UAE-Large-V1

WhereIsAI

sentence-transformers

feature-extraction

--- tags: - mteb - sentence_embedding - feature_extraction - sentence-transformers - transformers - transformers.js model-index: - name: UAE-Large-V1 results: - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (en) config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 75.55223880597015 - type: ap value: 38.264070815317794 - type: f1 value: 69.40977934769845 - task: type: Classification dataset: type: mteb/amazon_polarity name: MTEB AmazonPolarityClassification config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 92.84267499999999 - type: ap value: 89.57568507997713 - type: f1 value: 92.82590734337774 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (en) config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 48.292 - type: f1 value: 47.90257816032778 - task: type: Retrieval dataset: type: arguana name: MTEB ArguAna config: default split: test revision: None metrics: - type: map_at_1 value: 42.105 - type: map_at_10 value: 58.181000000000004 - type: map_at_100 value: 58.653999999999996 - type: map_at_1000 value: 58.657000000000004 - type: map_at_3 value: 54.386 - type: map_at_5 value: 56.757999999999996 - type: mrr_at_1 value: 42.745 - type: mrr_at_10 value: 58.437 - type: mrr_at_100 value: 58.894999999999996 - type: mrr_at_1000 value: 58.897999999999996 - type: mrr_at_3 value: 54.635 - type: mrr_at_5 value: 56.99999999999999 - type: ndcg_at_1 value: 42.105 - type: ndcg_at_10 value: 66.14999999999999 - type: ndcg_at_100 value: 68.048 - type: ndcg_at_1000 value: 68.11399999999999 - type: ndcg_at_3 value: 58.477000000000004 - type: ndcg_at_5 value: 62.768 - type: precision_at_1 value: 42.105 - type: precision_at_10 value: 9.110999999999999 - type: precision_at_100 value: 0.991 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 23.447000000000003 - type: precision_at_5 value: 16.159000000000002 - type: recall_at_1 value: 42.105 - type: recall_at_10 value: 91.11 - type: recall_at_100 value: 99.14699999999999 - type: recall_at_1000 value: 99.644 - type: recall_at_3 value: 70.341 - type: recall_at_5 value: 80.797 - task: type: Clustering dataset: type: mteb/arxiv-clustering-p2p name: MTEB ArxivClusteringP2P config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 49.02580759154173 - task: type: Clustering dataset: type: mteb/arxiv-clustering-s2s name: MTEB ArxivClusteringS2S config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 43.093601280163554 - task: type: Reranking dataset: type: mteb/askubuntudupquestions-reranking name: MTEB AskUbuntuDupQuestions config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 64.19590406875427 - type: mrr value: 77.09547992788991 - task: type: STS dataset: type: mteb/biosses-sts name: MTEB BIOSSES config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 87.86678362843676 - type: cos_sim_spearman value: 86.1423242570783 - type: euclidean_pearson value: 85.98994198511751 - type: euclidean_spearman value: 86.48209103503942 - type: manhattan_pearson value: 85.6446436316182 - type: manhattan_spearman value: 86.21039809734357 - task: type: Classification dataset: type: mteb/banking77 name: MTEB Banking77Classification config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 87.69155844155844 - type: f1 value: 87.68109381943547 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-p2p name: MTEB BiorxivClusteringP2P config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 39.37501687500394 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-s2s name: MTEB BiorxivClusteringS2S config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 37.23401405155885 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackAndroidRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.232 - type: map_at_10 value: 41.404999999999994 - type: map_at_100 value: 42.896 - type: map_at_1000 value: 43.028 - type: map_at_3 value: 37.925 - type: map_at_5 value: 39.865 - type: mrr_at_1 value: 36.338 - type: mrr_at_10 value: 46.969 - type: mrr_at_100 value: 47.684 - type: mrr_at_1000 value: 47.731 - type: mrr_at_3 value: 44.063 - type: mrr_at_5 value: 45.908 - type: ndcg_at_1 value: 36.338 - type: ndcg_at_10 value: 47.887 - type: ndcg_at_100 value: 53.357 - type: ndcg_at_1000 value: 55.376999999999995 - type: ndcg_at_3 value: 42.588 - type: ndcg_at_5 value: 45.132 - type: precision_at_1 value: 36.338 - type: precision_at_10 value: 9.17 - type: precision_at_100 value: 1.4909999999999999 - type: precision_at_1000 value: 0.196 - type: precision_at_3 value: 20.315 - type: precision_at_5 value: 14.793000000000001 - type: recall_at_1 value: 30.232 - type: recall_at_10 value: 60.67399999999999 - type: recall_at_100 value: 83.628 - type: recall_at_1000 value: 96.209 - type: recall_at_3 value: 45.48 - type: recall_at_5 value: 52.354 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackEnglishRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 32.237 - type: map_at_10 value: 42.829 - type: map_at_100 value: 44.065 - type: map_at_1000 value: 44.199 - type: map_at_3 value: 39.885999999999996 - type: map_at_5 value: 41.55 - type: mrr_at_1 value: 40.064 - type: mrr_at_10 value: 48.611 - type: mrr_at_100 value: 49.245 - type: mrr_at_1000 value: 49.29 - type: mrr_at_3 value: 46.561 - type: mrr_at_5 value: 47.771 - type: ndcg_at_1 value: 40.064 - type: ndcg_at_10 value: 48.388 - type: ndcg_at_100 value: 52.666999999999994 - type: ndcg_at_1000 value: 54.67100000000001 - type: ndcg_at_3 value: 44.504 - type: ndcg_at_5 value: 46.303 - type: precision_at_1 value: 40.064 - type: precision_at_10 value: 9.051 - type: precision_at_100 value: 1.4500000000000002 - type: precision_at_1000 value: 0.193 - type: precision_at_3 value: 21.444 - type: precision_at_5 value: 15.045 - type: recall_at_1 value: 32.237 - type: recall_at_10 value: 57.943999999999996 - type: recall_at_100 value: 75.98700000000001 - type: recall_at_1000 value: 88.453 - type: recall_at_3 value: 46.268 - type: recall_at_5 value: 51.459999999999994 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGamingRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 38.797 - type: map_at_10 value: 51.263000000000005 - type: map_at_100 value: 52.333 - type: map_at_1000 value: 52.393 - type: map_at_3 value: 47.936 - type: map_at_5 value: 49.844 - type: mrr_at_1 value: 44.389 - type: mrr_at_10 value: 54.601 - type: mrr_at_100 value: 55.300000000000004 - type: mrr_at_1000 value: 55.333 - type: mrr_at_3 value: 52.068999999999996 - type: mrr_at_5 value: 53.627 - type: ndcg_at_1 value: 44.389 - type: ndcg_at_10 value: 57.193000000000005 - type: ndcg_at_100 value: 61.307 - type: ndcg_at_1000 value: 62.529 - type: ndcg_at_3 value: 51.607 - type: ndcg_at_5 value: 54.409 - type: precision_at_1 value: 44.389 - type: precision_at_10 value: 9.26 - type: precision_at_100 value: 1.222 - type: precision_at_1000 value: 0.13699999999999998 - type: precision_at_3 value: 23.03 - type: precision_at_5 value: 15.887 - type: recall_at_1 value: 38.797 - type: recall_at_10 value: 71.449 - type: recall_at_100 value: 88.881 - type: recall_at_1000 value: 97.52 - type: recall_at_3 value: 56.503 - type: recall_at_5 value: 63.392 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGisRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 27.291999999999998 - type: map_at_10 value: 35.65 - type: map_at_100 value: 36.689 - type: map_at_1000 value: 36.753 - type: map_at_3 value: 32.995000000000005 - type: map_at_5 value: 34.409 - type: mrr_at_1 value: 29.04 - type: mrr_at_10 value: 37.486000000000004 - type: mrr_at_100 value: 38.394 - type: mrr_at_1000 value: 38.445 - type: mrr_at_3 value: 35.028 - type: mrr_at_5 value: 36.305 - type: ndcg_at_1 value: 29.04 - type: ndcg_at_10 value: 40.613 - type: ndcg_at_100 value: 45.733000000000004 - type: ndcg_at_1000 value: 47.447 - type: ndcg_at_3 value: 35.339999999999996 - type: ndcg_at_5 value: 37.706 - type: precision_at_1 value: 29.04 - type: precision_at_10 value: 6.192 - type: precision_at_100 value: 0.9249999999999999 - type: precision_at_1000 value: 0.11 - type: precision_at_3 value: 14.802000000000001 - type: precision_at_5 value: 10.305 - type: recall_at_1 value: 27.291999999999998 - type: recall_at_10 value: 54.25299999999999 - type: recall_at_100 value: 77.773 - type: recall_at_1000 value: 90.795 - type: recall_at_3 value: 39.731 - type: recall_at_5 value: 45.403999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackMathematicaRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 18.326 - type: map_at_10 value: 26.290999999999997 - type: map_at_100 value: 27.456999999999997 - type: map_at_1000 value: 27.583000000000002 - type: map_at_3 value: 23.578 - type: map_at_5 value: 25.113000000000003 - type: mrr_at_1 value: 22.637 - type: mrr_at_10 value: 31.139 - type: mrr_at_100 value: 32.074999999999996 - type: mrr_at_1000 value: 32.147 - type: mrr_at_3 value: 28.483000000000004 - type: mrr_at_5 value: 29.963 - type: ndcg_at_1 value: 22.637 - type: ndcg_at_10 value: 31.717000000000002 - type: ndcg_at_100 value: 37.201 - type: ndcg_at_1000 value: 40.088 - type: ndcg_at_3 value: 26.686 - type: ndcg_at_5 value: 29.076999999999998 - type: precision_at_1 value: 22.637 - type: precision_at_10 value: 5.7090000000000005 - type: precision_at_100 value: 0.979 - type: precision_at_1000 value: 0.13799999999999998 - type: precision_at_3 value: 12.894 - type: precision_at_5 value: 9.328 - type: recall_at_1 value: 18.326 - type: recall_at_10 value: 43.824999999999996 - type: recall_at_100 value: 67.316 - type: recall_at_1000 value: 87.481 - type: recall_at_3 value: 29.866999999999997 - type: recall_at_5 value: 35.961999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackPhysicsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 29.875 - type: map_at_10 value: 40.458 - type: map_at_100 value: 41.772 - type: map_at_1000 value: 41.882999999999996 - type: map_at_3 value: 37.086999999999996 - type: map_at_5 value: 39.153 - type: mrr_at_1 value: 36.381 - type: mrr_at_10 value: 46.190999999999995 - type: mrr_at_100 value: 46.983999999999995 - type: mrr_at_1000 value: 47.032000000000004 - type: mrr_at_3 value: 43.486999999999995 - type: mrr_at_5 value: 45.249 - type: ndcg_at_1 value: 36.381 - type: ndcg_at_10 value: 46.602 - type: ndcg_at_100 value: 51.885999999999996 - type: ndcg_at_1000 value: 53.895 - type: ndcg_at_3 value: 41.155 - type: ndcg_at_5 value: 44.182 - type: precision_at_1 value: 36.381 - type: precision_at_10 value: 8.402 - type: precision_at_100 value: 1.278 - type: precision_at_1000 value: 0.16199999999999998 - type: precision_at_3 value: 19.346 - type: precision_at_5 value: 14.09 - type: recall_at_1 value: 29.875 - type: recall_at_10 value: 59.065999999999995 - type: recall_at_100 value: 80.923 - type: recall_at_1000 value: 93.927 - type: recall_at_3 value: 44.462 - type: recall_at_5 value: 51.89 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackProgrammersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.94 - type: map_at_10 value: 35.125 - type: map_at_100 value: 36.476 - type: map_at_1000 value: 36.579 - type: map_at_3 value: 31.840000000000003 - type: map_at_5 value: 33.647 - type: mrr_at_1 value: 30.936000000000003 - type: mrr_at_10 value: 40.637 - type: mrr_at_100 value: 41.471000000000004 - type: mrr_at_1000 value: 41.525 - type: mrr_at_3 value: 38.013999999999996 - type: mrr_at_5 value: 39.469 - type: ndcg_at_1 value: 30.936000000000003 - type: ndcg_at_10 value: 41.295 - type: ndcg_at_100 value: 46.92 - type: ndcg_at_1000 value: 49.183 - type: ndcg_at_3 value: 35.811 - type: ndcg_at_5 value: 38.306000000000004 - type: precision_at_1 value: 30.936000000000003 - type: precision_at_10 value: 7.728 - type: precision_at_100 value: 1.226 - type: precision_at_1000 value: 0.158 - type: precision_at_3 value: 17.237 - type: precision_at_5 value: 12.42 - type: recall_at_1 value: 24.94 - type: recall_at_10 value: 54.235 - type: recall_at_100 value: 78.314 - type: recall_at_1000 value: 93.973 - type: recall_at_3 value: 38.925 - type: recall_at_5 value: 45.505 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 26.250833333333333 - type: map_at_10 value: 35.46875 - type: map_at_100 value: 36.667 - type: map_at_1000 value: 36.78025 - type: map_at_3 value: 32.56733333333334 - type: map_at_5 value: 34.20333333333333 - type: mrr_at_1 value: 30.8945 - type: mrr_at_10 value: 39.636833333333335 - type: mrr_at_100 value: 40.46508333333333 - type: mrr_at_1000 value: 40.521249999999995 - type: mrr_at_3 value: 37.140166666666666 - type: mrr_at_5 value: 38.60999999999999 - type: ndcg_at_1 value: 30.8945 - type: ndcg_at_10 value: 40.93441666666667 - type: ndcg_at_100 value: 46.062416666666664 - type: ndcg_at_1000 value: 48.28341666666667 - type: ndcg_at_3 value: 35.97575 - type: ndcg_at_5 value: 38.3785 - type: precision_at_1 value: 30.8945 - type: precision_at_10 value: 7.180250000000001 - type: precision_at_100 value: 1.1468333333333334 - type: precision_at_1000 value: 0.15283333333333332 - type: precision_at_3 value: 16.525583333333334 - type: precision_at_5 value: 11.798333333333332 - type: recall_at_1 value: 26.250833333333333 - type: recall_at_10 value: 52.96108333333333 - type: recall_at_100 value: 75.45908333333334 - type: recall_at_1000 value: 90.73924999999998 - type: recall_at_3 value: 39.25483333333333 - type: recall_at_5 value: 45.37950000000001 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackStatsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.595 - type: map_at_10 value: 31.747999999999998 - type: map_at_100 value: 32.62 - type: map_at_1000 value: 32.713 - type: map_at_3 value: 29.48 - type: map_at_5 value: 30.635 - type: mrr_at_1 value: 27.607 - type: mrr_at_10 value: 34.449000000000005 - type: mrr_at_100 value: 35.182 - type: mrr_at_1000 value: 35.254000000000005 - type: mrr_at_3 value: 32.413 - type: mrr_at_5 value: 33.372 - type: ndcg_at_1 value: 27.607 - type: ndcg_at_10 value: 36.041000000000004 - type: ndcg_at_100 value: 40.514 - type: ndcg_at_1000 value: 42.851 - type: ndcg_at_3 value: 31.689 - type: ndcg_at_5 value: 33.479 - type: precision_at_1 value: 27.607 - type: precision_at_10 value: 5.66 - type: precision_at_100 value: 0.868 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_3 value: 13.446 - type: precision_at_5 value: 9.264 - type: recall_at_1 value: 24.595 - type: recall_at_10 value: 46.79 - type: recall_at_100 value: 67.413 - type: recall_at_1000 value: 84.753 - type: recall_at_3 value: 34.644999999999996 - type: recall_at_5 value: 39.09 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackTexRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 17.333000000000002 - type: map_at_10 value: 24.427 - type: map_at_100 value: 25.576 - type: map_at_1000 value: 25.692999999999998 - type: map_at_3 value: 22.002 - type: map_at_5 value: 23.249 - type: mrr_at_1 value: 20.716 - type: mrr_at_10 value: 28.072000000000003 - type: mrr_at_100 value: 29.067 - type: mrr_at_1000 value: 29.137 - type: mrr_at_3 value: 25.832 - type: mrr_at_5 value: 27.045 - type: ndcg_at_1 value: 20.716 - type: ndcg_at_10 value: 29.109 - type: ndcg_at_100 value: 34.797 - type: ndcg_at_1000 value: 37.503 - type: ndcg_at_3 value: 24.668 - type: ndcg_at_5 value: 26.552999999999997 - type: precision_at_1 value: 20.716 - type: precision_at_10 value: 5.351 - type: precision_at_100 value: 0.955 - type: precision_at_1000 value: 0.136 - type: precision_at_3 value: 11.584999999999999 - type: precision_at_5 value: 8.362 - type: recall_at_1 value: 17.333000000000002 - type: recall_at_10 value: 39.604 - type: recall_at_100 value: 65.525 - type: recall_at_1000 value: 84.651 - type: recall_at_3 value: 27.199 - type: recall_at_5 value: 32.019 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackUnixRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 26.342 - type: map_at_10 value: 35.349000000000004 - type: map_at_100 value: 36.443 - type: map_at_1000 value: 36.548 - type: map_at_3 value: 32.307 - type: map_at_5 value: 34.164 - type: mrr_at_1 value: 31.063000000000002 - type: mrr_at_10 value: 39.703 - type: mrr_at_100 value: 40.555 - type: mrr_at_1000 value: 40.614 - type: mrr_at_3 value: 37.141999999999996 - type: mrr_at_5 value: 38.812000000000005 - type: ndcg_at_1 value: 31.063000000000002 - type: ndcg_at_10 value: 40.873 - type: ndcg_at_100 value: 45.896 - type: ndcg_at_1000 value: 48.205999999999996 - type: ndcg_at_3 value: 35.522 - type: ndcg_at_5 value: 38.419 - type: precision_at_1 value: 31.063000000000002 - type: precision_at_10 value: 6.866 - type: precision_at_100 value: 1.053 - type: precision_at_1000 value: 0.13699999999999998 - type: precision_at_3 value: 16.014 - type: precision_at_5 value: 11.604000000000001 - type: recall_at_1 value: 26.342 - type: recall_at_10 value: 53.40200000000001 - type: recall_at_100 value: 75.251 - type: recall_at_1000 value: 91.13799999999999 - type: recall_at_3 value: 39.103 - type: recall_at_5 value: 46.357 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWebmastersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 23.71 - type: map_at_10 value: 32.153999999999996 - type: map_at_100 value: 33.821 - type: map_at_1000 value: 34.034 - type: map_at_3 value: 29.376 - type: map_at_5 value: 30.878 - type: mrr_at_1 value: 28.458 - type: mrr_at_10 value: 36.775999999999996 - type: mrr_at_100 value: 37.804 - type: mrr_at_1000 value: 37.858999999999995 - type: mrr_at_3 value: 34.123999999999995 - type: mrr_at_5 value: 35.596 - type: ndcg_at_1 value: 28.458 - type: ndcg_at_10 value: 37.858999999999995 - type: ndcg_at_100 value: 44.194 - type: ndcg_at_1000 value: 46.744 - type: ndcg_at_3 value: 33.348 - type: ndcg_at_5 value: 35.448 - type: precision_at_1 value: 28.458 - type: precision_at_10 value: 7.4510000000000005 - type: precision_at_100 value: 1.5 - type: precision_at_1000 value: 0.23700000000000002 - type: precision_at_3 value: 15.809999999999999 - type: precision_at_5 value: 11.462 - type: recall_at_1 value: 23.71 - type: recall_at_10 value: 48.272999999999996 - type: recall_at_100 value: 77.134 - type: recall_at_1000 value: 93.001 - type: recall_at_3 value: 35.480000000000004 - type: recall_at_5 value: 41.19 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWordpressRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 21.331 - type: map_at_10 value: 28.926000000000002 - type: map_at_100 value: 29.855999999999998 - type: map_at_1000 value: 29.957 - type: map_at_3 value: 26.395999999999997 - type: map_at_5 value: 27.933000000000003 - type: mrr_at_1 value: 23.105 - type: mrr_at_10 value: 31.008000000000003 - type: mrr_at_100 value: 31.819999999999997 - type: mrr_at_1000 value: 31.887999999999998 - type: mrr_at_3 value: 28.466 - type: mrr_at_5 value: 30.203000000000003 - type: ndcg_at_1 value: 23.105 - type: ndcg_at_10 value: 33.635999999999996 - type: ndcg_at_100 value: 38.277 - type: ndcg_at_1000 value: 40.907 - type: ndcg_at_3 value: 28.791 - type: ndcg_at_5 value: 31.528 - type: precision_at_1 value: 23.105 - type: precision_at_10 value: 5.323 - type: precision_at_100 value: 0.815 - type: precision_at_1000 value: 0.117 - type: precision_at_3 value: 12.384 - type: precision_at_5 value: 9.02 - type: recall_at_1 value: 21.331 - type: recall_at_10 value: 46.018 - type: recall_at_100 value: 67.364 - type: recall_at_1000 value: 86.97 - type: recall_at_3 value: 33.395 - type: recall_at_5 value: 39.931 - task: type: Retrieval dataset: type: climate-fever name: MTEB ClimateFEVER config: default split: test revision: None metrics: - type: map_at_1 value: 17.011000000000003 - type: map_at_10 value: 28.816999999999997 - type: map_at_100 value: 30.761 - type: map_at_1000 value: 30.958000000000002 - type: map_at_3 value: 24.044999999999998 - type: map_at_5 value: 26.557 - type: mrr_at_1 value: 38.696999999999996 - type: mrr_at_10 value: 50.464 - type: mrr_at_100 value: 51.193999999999996 - type: mrr_at_1000 value: 51.219 - type: mrr_at_3 value: 47.339999999999996 - type: mrr_at_5 value: 49.346000000000004 - type: ndcg_at_1 value: 38.696999999999996 - type: ndcg_at_10 value: 38.53 - type: ndcg_at_100 value: 45.525 - type: ndcg_at_1000 value: 48.685 - type: ndcg_at_3 value: 32.282 - type: ndcg_at_5 value: 34.482 - type: precision_at_1 value: 38.696999999999996 - type: precision_at_10 value: 11.895999999999999 - type: precision_at_100 value: 1.95 - type: precision_at_1000 value: 0.254 - type: precision_at_3 value: 24.038999999999998 - type: precision_at_5 value: 18.332 - type: recall_at_1 value: 17.011000000000003 - type: recall_at_10 value: 44.452999999999996 - type: recall_at_100 value: 68.223 - type: recall_at_1000 value: 85.653 - type: recall_at_3 value: 28.784 - type: recall_at_5 value: 35.66 - task: type: Retrieval dataset: type: dbpedia-entity name: MTEB DBPedia config: default split: test revision: None metrics: - type: map_at_1 value: 9.516 - type: map_at_10 value: 21.439 - type: map_at_100 value: 31.517 - type: map_at_1000 value: 33.267 - type: map_at_3 value: 15.004999999999999 - type: map_at_5 value: 17.793999999999997 - type: mrr_at_1 value: 71.25 - type: mrr_at_10 value: 79.071 - type: mrr_at_100 value: 79.325 - type: mrr_at_1000 value: 79.33 - type: mrr_at_3 value: 77.708 - type: mrr_at_5 value: 78.546 - type: ndcg_at_1 value: 58.62500000000001 - type: ndcg_at_10 value: 44.889 - type: ndcg_at_100 value: 50.536 - type: ndcg_at_1000 value: 57.724 - type: ndcg_at_3 value: 49.32 - type: ndcg_at_5 value: 46.775 - type: precision_at_1 value: 71.25 - type: precision_at_10 value: 36.175000000000004 - type: precision_at_100 value: 11.940000000000001 - type: precision_at_1000 value: 2.178 - type: precision_at_3 value: 53.583000000000006 - type: precision_at_5 value: 45.550000000000004 - type: recall_at_1 value: 9.516 - type: recall_at_10 value: 27.028000000000002 - type: recall_at_100 value: 57.581 - type: recall_at_1000 value: 80.623 - type: recall_at_3 value: 16.313 - type: recall_at_5 value: 20.674 - task: type: Classification dataset: type: mteb/emotion name: MTEB EmotionClassification config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 51.74999999999999 - type: f1 value: 46.46706502669774 - task: type: Retrieval dataset: type: fever name: MTEB FEVER config: default split: test revision: None metrics: - type: map_at_1 value: 77.266 - type: map_at_10 value: 84.89999999999999 - type: map_at_100 value: 85.109 - type: map_at_1000 value: 85.123 - type: map_at_3 value: 83.898 - type: map_at_5 value: 84.541 - type: mrr_at_1 value: 83.138 - type: mrr_at_10 value: 89.37 - type: mrr_at_100 value: 89.432 - type: mrr_at_1000 value: 89.43299999999999 - type: mrr_at_3 value: 88.836 - type: mrr_at_5 value: 89.21 - type: ndcg_at_1 value: 83.138 - type: ndcg_at_10 value: 88.244 - type: ndcg_at_100 value: 88.98700000000001 - type: ndcg_at_1000 value: 89.21900000000001 - type: ndcg_at_3 value: 86.825 - type: ndcg_at_5 value: 87.636 - type: precision_at_1 value: 83.138 - type: precision_at_10 value: 10.47 - type: precision_at_100 value: 1.1079999999999999 - type: precision_at_1000 value: 0.11499999999999999 - type: precision_at_3 value: 32.933 - type: precision_at_5 value: 20.36 - type: recall_at_1 value: 77.266 - type: recall_at_10 value: 94.063 - type: recall_at_100 value: 96.993 - type: recall_at_1000 value: 98.414 - type: recall_at_3 value: 90.228 - type: recall_at_5 value: 92.328 - task: type: Retrieval dataset: type: fiqa name: MTEB FiQA2018 config: default split: test revision: None metrics: - type: map_at_1 value: 22.319 - type: map_at_10 value: 36.943 - type: map_at_100 value: 38.951 - type: map_at_1000 value: 39.114 - type: map_at_3 value: 32.82 - type: map_at_5 value: 34.945 - type: mrr_at_1 value: 44.135999999999996 - type: mrr_at_10 value: 53.071999999999996 - type: mrr_at_100 value: 53.87 - type: mrr_at_1000 value: 53.90200000000001 - type: mrr_at_3 value: 50.77199999999999 - type: mrr_at_5 value: 52.129999999999995 - type: ndcg_at_1 value: 44.135999999999996 - type: ndcg_at_10 value: 44.836 - type: ndcg_at_100 value: 51.754 - type: ndcg_at_1000 value: 54.36 - type: ndcg_at_3 value: 41.658 - type: ndcg_at_5 value: 42.354 - type: precision_at_1 value: 44.135999999999996 - type: precision_at_10 value: 12.284 - type: precision_at_100 value: 1.952 - type: precision_at_1000 value: 0.242 - type: precision_at_3 value: 27.828999999999997 - type: precision_at_5 value: 20.093 - type: recall_at_1 value: 22.319 - type: recall_at_10 value: 51.528 - type: recall_at_100 value: 76.70700000000001 - type: recall_at_1000 value: 92.143 - type: recall_at_3 value: 38.641 - type: recall_at_5 value: 43.653999999999996 - task: type: Retrieval dataset: type: hotpotqa name: MTEB HotpotQA config: default split: test revision: None metrics: - type: map_at_1 value: 40.182 - type: map_at_10 value: 65.146 - type: map_at_100 value: 66.023 - type: map_at_1000 value: 66.078 - type: map_at_3 value: 61.617999999999995 - type: map_at_5 value: 63.82299999999999 - type: mrr_at_1 value: 80.365 - type: mrr_at_10 value: 85.79 - type: mrr_at_100 value: 85.963 - type: mrr_at_1000 value: 85.968 - type: mrr_at_3 value: 84.952 - type: mrr_at_5 value: 85.503 - type: ndcg_at_1 value: 80.365 - type: ndcg_at_10 value: 73.13499999999999 - type: ndcg_at_100 value: 76.133 - type: ndcg_at_1000 value: 77.151 - type: ndcg_at_3 value: 68.255 - type: ndcg_at_5 value: 70.978 - type: precision_at_1 value: 80.365 - type: precision_at_10 value: 15.359 - type: precision_at_100 value: 1.7690000000000001 - type: precision_at_1000 value: 0.19 - type: precision_at_3 value: 44.024 - type: precision_at_5 value: 28.555999999999997 - type: recall_at_1 value: 40.182 - type: recall_at_10 value: 76.793 - type: recall_at_100 value: 88.474 - type: recall_at_1000 value: 95.159 - type: recall_at_3 value: 66.036 - type: recall_at_5 value: 71.391 - task: type: Classification dataset: type: mteb/imdb name: MTEB ImdbClassification config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 92.7796 - type: ap value: 89.24883716810874 - type: f1 value: 92.7706903433313 - task: type: Retrieval dataset: type: msmarco name: MTEB MSMARCO config: default split: dev revision: None metrics: - type: map_at_1 value: 22.016 - type: map_at_10 value: 34.408 - type: map_at_100 value: 35.592 - type: map_at_1000 value: 35.64 - type: map_at_3 value: 30.459999999999997 - type: map_at_5 value: 32.721000000000004 - type: mrr_at_1 value: 22.593 - type: mrr_at_10 value: 34.993 - type: mrr_at_100 value: 36.113 - type: mrr_at_1000 value: 36.156 - type: mrr_at_3 value: 31.101 - type: mrr_at_5 value: 33.364 - type: ndcg_at_1 value: 22.579 - type: ndcg_at_10 value: 41.404999999999994 - type: ndcg_at_100 value: 47.018 - type: ndcg_at_1000 value: 48.211999999999996 - type: ndcg_at_3 value: 33.389 - type: ndcg_at_5 value: 37.425000000000004 - type: precision_at_1 value: 22.579 - type: precision_at_10 value: 6.59 - type: precision_at_100 value: 0.938 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 14.241000000000001 - type: precision_at_5 value: 10.59 - type: recall_at_1 value: 22.016 - type: recall_at_10 value: 62.927 - type: recall_at_100 value: 88.72 - type: recall_at_1000 value: 97.80799999999999 - type: recall_at_3 value: 41.229 - type: recall_at_5 value: 50.88 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (en) config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 94.01732786137711 - type: f1 value: 93.76353126402202 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (en) config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 76.91746466028272 - type: f1 value: 57.715651682646765 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (en) config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 76.5030262273033 - type: f1 value: 74.6693629986121 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (en) config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 79.74781439139207 - type: f1 value: 79.96684171018774 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-p2p name: MTEB MedrxivClusteringP2P config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 33.2156206892017 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-s2s name: MTEB MedrxivClusteringS2S config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 31.180539484816137 - task: type: Reranking dataset: type: mteb/mind_small name: MTEB MindSmallReranking config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 32.51125957874274 - type: mrr value: 33.777037359249995 - task: type: Retrieval dataset: type: nfcorpus name: MTEB NFCorpus config: default split: test revision: None metrics: - type: map_at_1 value: 7.248 - type: map_at_10 value: 15.340000000000002 - type: map_at_100 value: 19.591 - type: map_at_1000 value: 21.187 - type: map_at_3 value: 11.329 - type: map_at_5 value: 13.209999999999999 - type: mrr_at_1 value: 47.678 - type: mrr_at_10 value: 57.493 - type: mrr_at_100 value: 58.038999999999994 - type: mrr_at_1000 value: 58.07 - type: mrr_at_3 value: 55.36600000000001 - type: mrr_at_5 value: 56.635999999999996 - type: ndcg_at_1 value: 46.129999999999995 - type: ndcg_at_10 value: 38.653999999999996 - type: ndcg_at_100 value: 36.288 - type: ndcg_at_1000 value: 44.765 - type: ndcg_at_3 value: 43.553 - type: ndcg_at_5 value: 41.317 - type: precision_at_1 value: 47.368 - type: precision_at_10 value: 28.669 - type: precision_at_100 value: 9.158 - type: precision_at_1000 value: 2.207 - type: precision_at_3 value: 40.97 - type: precision_at_5 value: 35.604 - type: recall_at_1 value: 7.248 - type: recall_at_10 value: 19.46 - type: recall_at_100 value: 37.214000000000006 - type: recall_at_1000 value: 67.64099999999999 - type: recall_at_3 value: 12.025 - type: recall_at_5 value: 15.443999999999999 - task: type: Retrieval dataset: type: nq name: MTEB NQ config: default split: test revision: None metrics: - type: map_at_1 value: 31.595000000000002 - type: map_at_10 value: 47.815999999999995 - type: map_at_100 value: 48.811 - type: map_at_1000 value: 48.835 - type: map_at_3 value: 43.225 - type: map_at_5 value: 46.017 - type: mrr_at_1 value: 35.689 - type: mrr_at_10 value: 50.341 - type: mrr_at_100 value: 51.044999999999995 - type: mrr_at_1000 value: 51.062 - type: mrr_at_3 value: 46.553 - type: mrr_at_5 value: 48.918 - type: ndcg_at_1 value: 35.66 - type: ndcg_at_10 value: 55.859 - type: ndcg_at_100 value: 59.864 - type: ndcg_at_1000 value: 60.419999999999995 - type: ndcg_at_3 value: 47.371 - type: ndcg_at_5 value: 51.995000000000005 - type: precision_at_1 value: 35.66 - type: precision_at_10 value: 9.27 - type: precision_at_100 value: 1.1520000000000001 - type: precision_at_1000 value: 0.12 - type: precision_at_3 value: 21.63 - type: precision_at_5 value: 15.655 - type: recall_at_1 value: 31.595000000000002 - type: recall_at_10 value: 77.704 - type: recall_at_100 value: 94.774 - type: recall_at_1000 value: 98.919 - type: recall_at_3 value: 56.052 - type: recall_at_5 value: 66.623 - task: type: Retrieval dataset: type: quora name: MTEB QuoraRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 71.489 - type: map_at_10 value: 85.411 - type: map_at_100 value: 86.048 - type: map_at_1000 value: 86.064 - type: map_at_3 value: 82.587 - type: map_at_5 value: 84.339 - type: mrr_at_1 value: 82.28 - type: mrr_at_10 value: 88.27199999999999 - type: mrr_at_100 value: 88.362 - type: mrr_at_1000 value: 88.362 - type: mrr_at_3 value: 87.372 - type: mrr_at_5 value: 87.995 - type: ndcg_at_1 value: 82.27 - type: ndcg_at_10 value: 89.023 - type: ndcg_at_100 value: 90.191 - type: ndcg_at_1000 value: 90.266 - type: ndcg_at_3 value: 86.37 - type: ndcg_at_5 value: 87.804 - type: precision_at_1 value: 82.27 - type: precision_at_10 value: 13.469000000000001 - type: precision_at_100 value: 1.533 - type: precision_at_1000 value: 0.157 - type: precision_at_3 value: 37.797 - type: precision_at_5 value: 24.734 - type: recall_at_1 value: 71.489 - type: recall_at_10 value: 95.824 - type: recall_at_100 value: 99.70599999999999 - type: recall_at_1000 value: 99.979 - type: recall_at_3 value: 88.099 - type: recall_at_5 value: 92.285 - task: type: Clustering dataset: type: mteb/reddit-clustering name: MTEB RedditClustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 60.52398807444541 - task: type: Clustering dataset: type: mteb/reddit-clustering-p2p name: MTEB RedditClusteringP2P config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 65.34855891507871 - task: type: Retrieval dataset: type: scidocs name: MTEB SCIDOCS config: default split: test revision: None metrics: - type: map_at_1 value: 5.188000000000001 - type: map_at_10 value: 13.987 - type: map_at_100 value: 16.438 - type: map_at_1000 value: 16.829 - type: map_at_3 value: 9.767000000000001 - type: map_at_5 value: 11.912 - type: mrr_at_1 value: 25.6 - type: mrr_at_10 value: 37.744 - type: mrr_at_100 value: 38.847 - type: mrr_at_1000 value: 38.894 - type: mrr_at_3 value: 34.166999999999994 - type: mrr_at_5 value: 36.207 - type: ndcg_at_1 value: 25.6 - type: ndcg_at_10 value: 22.980999999999998 - type: ndcg_at_100 value: 32.039 - type: ndcg_at_1000 value: 38.157000000000004 - type: ndcg_at_3 value: 21.567 - type: ndcg_at_5 value: 19.070999999999998 - type: precision_at_1 value: 25.6 - type: precision_at_10 value: 12.02 - type: precision_at_100 value: 2.5100000000000002 - type: precision_at_1000 value: 0.396 - type: precision_at_3 value: 20.333000000000002 - type: precision_at_5 value: 16.98 - type: recall_at_1 value: 5.188000000000001 - type: recall_at_10 value: 24.372 - type: recall_at_100 value: 50.934999999999995 - type: recall_at_1000 value: 80.477 - type: recall_at_3 value: 12.363 - type: recall_at_5 value: 17.203 - task: type: STS dataset: type: mteb/sickr-sts name: MTEB SICK-R config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 87.24286275535398 - type: cos_sim_spearman value: 82.62333770991818 - type: euclidean_pearson value: 84.60353717637284 - type: euclidean_spearman value: 82.32990108810047 - type: manhattan_pearson value: 84.6089049738196 - type: manhattan_spearman value: 82.33361785438936 - task: type: STS dataset: type: mteb/sts12-sts name: MTEB STS12 config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 87.87428858503165 - type: cos_sim_spearman value: 79.09145886519929 - type: euclidean_pearson value: 86.42669231664036 - type: euclidean_spearman value: 80.03127375435449 - type: manhattan_pearson value: 86.41330338305022 - type: manhattan_spearman value: 80.02492538673368 - task: type: STS dataset: type: mteb/sts13-sts name: MTEB STS13 config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 88.67912277322645 - type: cos_sim_spearman value: 89.6171319711762 - type: euclidean_pearson value: 86.56571917398725 - type: euclidean_spearman value: 87.71216907898948 - type: manhattan_pearson value: 86.57459050182473 - type: manhattan_spearman value: 87.71916648349993 - task: type: STS dataset: type: mteb/sts14-sts name: MTEB STS14 config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 86.71957379085862 - type: cos_sim_spearman value: 85.01784075851465 - type: euclidean_pearson value: 84.7407848472801 - type: euclidean_spearman value: 84.61063091345538 - type: manhattan_pearson value: 84.71494352494403 - type: manhattan_spearman value: 84.58772077604254 - task: type: STS dataset: type: mteb/sts15-sts name: MTEB STS15 config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 88.40508326325175 - type: cos_sim_spearman value: 89.50912897763186 - type: euclidean_pearson value: 87.82349070086627 - type: euclidean_spearman value: 88.44179162727521 - type: manhattan_pearson value: 87.80181927025595 - type: manhattan_spearman value: 88.43205129636243 - task: type: STS dataset: type: mteb/sts16-sts name: MTEB STS16 config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 85.35846741715478 - type: cos_sim_spearman value: 86.61172476741842 - type: euclidean_pearson value: 84.60123125491637 - type: euclidean_spearman value: 85.3001948141827 - type: manhattan_pearson value: 84.56231142658329 - type: manhattan_spearman value: 85.23579900798813 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-en) config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 88.94539129818824 - type: cos_sim_spearman value: 88.99349064256742 - type: euclidean_pearson value: 88.7142444640351 - type: euclidean_spearman value: 88.34120813505011 - type: manhattan_pearson value: 88.70363008238084 - type: manhattan_spearman value: 88.31952816956954 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (en) config: en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 68.29910260369893 - type: cos_sim_spearman value: 68.79263346213466 - type: euclidean_pearson value: 68.41627521422252 - type: euclidean_spearman value: 66.61602587398579 - type: manhattan_pearson value: 68.49402183447361 - type: manhattan_spearman value: 66.80157792354453 - task: type: STS dataset: type: mteb/stsbenchmark-sts name: MTEB STSBenchmark config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 87.43703906343708 - type: cos_sim_spearman value: 89.06081805093662 - type: euclidean_pearson value: 87.48311456299662 - type: euclidean_spearman value: 88.07417597580013 - type: manhattan_pearson value: 87.48202249768894 - type: manhattan_spearman value: 88.04758031111642 - task: type: Reranking dataset: type: mteb/scidocs-reranking name: MTEB SciDocsRR config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 87.49080620485203 - type: mrr value: 96.19145378949301 - task: type: Retrieval dataset: type: scifact name: MTEB SciFact config: default split: test revision: None metrics: - type: map_at_1 value: 59.317 - type: map_at_10 value: 69.296 - type: map_at_100 value: 69.738 - type: map_at_1000 value: 69.759 - type: map_at_3 value: 66.12599999999999 - type: map_at_5 value: 67.532 - type: mrr_at_1 value: 62 - type: mrr_at_10 value: 70.176 - type: mrr_at_100 value: 70.565 - type: mrr_at_1000 value: 70.583 - type: mrr_at_3 value: 67.833 - type: mrr_at_5 value: 68.93299999999999 - type: ndcg_at_1 value: 62 - type: ndcg_at_10 value: 74.069 - type: ndcg_at_100 value: 76.037 - type: ndcg_at_1000 value: 76.467 - type: ndcg_at_3 value: 68.628 - type: ndcg_at_5 value: 70.57600000000001 - type: precision_at_1 value: 62 - type: precision_at_10 value: 10 - type: precision_at_100 value: 1.097 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_3 value: 26.667 - type: precision_at_5 value: 17.4 - type: recall_at_1 value: 59.317 - type: recall_at_10 value: 87.822 - type: recall_at_100 value: 96.833 - type: recall_at_1000 value: 100 - type: recall_at_3 value: 73.06099999999999 - type: recall_at_5 value: 77.928 - task: type: PairClassification dataset: type: mteb/sprintduplicatequestions-pairclassification name: MTEB SprintDuplicateQuestions config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.88910891089108 - type: cos_sim_ap value: 97.236958456951 - type: cos_sim_f1 value: 94.39999999999999 - type: cos_sim_precision value: 94.39999999999999 - type: cos_sim_recall value: 94.39999999999999 - type: dot_accuracy value: 99.82574257425742 - type: dot_ap value: 94.94344759441888 - type: dot_f1 value: 91.17352056168507 - type: dot_precision value: 91.44869215291752 - type: dot_recall value: 90.9 - type: euclidean_accuracy value: 99.88415841584158 - type: euclidean_ap value: 97.2044250782305 - type: euclidean_f1 value: 94.210786739238 - type: euclidean_precision value: 93.24191968658178 - type: euclidean_recall value: 95.19999999999999 - type: manhattan_accuracy value: 99.88613861386139 - type: manhattan_ap value: 97.20683205497689 - type: manhattan_f1 value: 94.2643391521197 - type: manhattan_precision value: 94.02985074626866 - type: manhattan_recall value: 94.5 - type: max_accuracy value: 99.88910891089108 - type: max_ap value: 97.236958456951 - type: max_f1 value: 94.39999999999999 - task: type: Clustering dataset: type: mteb/stackexchange-clustering name: MTEB StackExchangeClustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 66.53940781726187 - task: type: Clustering dataset: type: mteb/stackexchange-clustering-p2p name: MTEB StackExchangeClusteringP2P config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 36.71865011295108 - task: type: Reranking dataset: type: mteb/stackoverflowdupquestions-reranking name: MTEB StackOverflowDupQuestions config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 55.3218674533331 - type: mrr value: 56.28279910449028 - task: type: Summarization dataset: type: mteb/summeval name: MTEB SummEval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 30.723915667479673 - type: cos_sim_spearman value: 32.029070449745234 - type: dot_pearson value: 28.864944212481454 - type: dot_spearman value: 27.939266999596725 - task: type: Retrieval dataset: type: trec-covid name: MTEB TRECCOVID config: default split: test revision: None metrics: - type: map_at_1 value: 0.231 - type: map_at_10 value: 1.949 - type: map_at_100 value: 10.023 - type: map_at_1000 value: 23.485 - type: map_at_3 value: 0.652 - type: map_at_5 value: 1.054 - type: mrr_at_1 value: 86 - type: mrr_at_10 value: 92.067 - type: mrr_at_100 value: 92.067 - type: mrr_at_1000 value: 92.067 - type: mrr_at_3 value: 91.667 - type: mrr_at_5 value: 92.067 - type: ndcg_at_1 value: 83 - type: ndcg_at_10 value: 76.32900000000001 - type: ndcg_at_100 value: 54.662 - type: ndcg_at_1000 value: 48.062 - type: ndcg_at_3 value: 81.827 - type: ndcg_at_5 value: 80.664 - type: precision_at_1 value: 86 - type: precision_at_10 value: 80 - type: precision_at_100 value: 55.48 - type: precision_at_1000 value: 20.938000000000002 - type: precision_at_3 value: 85.333 - type: precision_at_5 value: 84.39999999999999 - type: recall_at_1 value: 0.231 - type: recall_at_10 value: 2.158 - type: recall_at_100 value: 13.344000000000001 - type: recall_at_1000 value: 44.31 - type: recall_at_3 value: 0.6779999999999999 - type: recall_at_5 value: 1.13 - task: type: Retrieval dataset: type: webis-touche2020 name: MTEB Touche2020 config: default split: test revision: None metrics: - type: map_at_1 value: 2.524 - type: map_at_10 value: 10.183 - type: map_at_100 value: 16.625 - type: map_at_1000 value: 18.017 - type: map_at_3 value: 5.169 - type: map_at_5 value: 6.772 - type: mrr_at_1 value: 32.653 - type: mrr_at_10 value: 47.128 - type: mrr_at_100 value: 48.458 - type: mrr_at_1000 value: 48.473 - type: mrr_at_3 value: 44.897999999999996 - type: mrr_at_5 value: 45.306000000000004 - type: ndcg_at_1 value: 30.612000000000002 - type: ndcg_at_10 value: 24.928 - type: ndcg_at_100 value: 37.613 - type: ndcg_at_1000 value: 48.528 - type: ndcg_at_3 value: 28.829 - type: ndcg_at_5 value: 25.237 - type: precision_at_1 value: 32.653 - type: precision_at_10 value: 22.448999999999998 - type: precision_at_100 value: 8.02 - type: precision_at_1000 value: 1.537 - type: precision_at_3 value: 30.612000000000002 - type: precision_at_5 value: 24.490000000000002 - type: recall_at_1 value: 2.524 - type: recall_at_10 value: 16.38 - type: recall_at_100 value: 49.529 - type: recall_at_1000 value: 83.598 - type: recall_at_3 value: 6.411 - type: recall_at_5 value: 8.932 - task: type: Classification dataset: type: mteb/toxic_conversations_50k name: MTEB ToxicConversationsClassification config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 71.09020000000001 - type: ap value: 14.451710060978993 - type: f1 value: 54.7874410609049 - task: type: Classification dataset: type: mteb/tweet_sentiment_extraction name: MTEB TweetSentimentExtractionClassification config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 59.745331069609506 - type: f1 value: 60.08387848592697 - task: type: Clustering dataset: type: mteb/twentynewsgroups-clustering name: MTEB TwentyNewsgroupsClustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 51.71549485462037 - task: type: PairClassification dataset: type: mteb/twittersemeval2015-pairclassification name: MTEB TwitterSemEval2015 config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 87.39345532574357 - type: cos_sim_ap value: 78.16796549696478 - type: cos_sim_f1 value: 71.27713276123171 - type: cos_sim_precision value: 68.3115626511853 - type: cos_sim_recall value: 74.51187335092348 - type: dot_accuracy value: 85.12248912201228 - type: dot_ap value: 69.26039256107077 - type: dot_f1 value: 65.04294321240867 - type: dot_precision value: 63.251059586138126 - type: dot_recall value: 66.93931398416886 - type: euclidean_accuracy value: 87.07754664123503 - type: euclidean_ap value: 77.7872176038945 - type: euclidean_f1 value: 70.85587801278899 - type: euclidean_precision value: 66.3519115614924 - type: euclidean_recall value: 76.01583113456465 - type: manhattan_accuracy value: 87.07754664123503 - type: manhattan_ap value: 77.7341400185556 - type: manhattan_f1 value: 70.80310880829015 - type: manhattan_precision value: 69.54198473282443 - type: manhattan_recall value: 72.1108179419525 - type: max_accuracy value: 87.39345532574357 - type: max_ap value: 78.16796549696478 - type: max_f1 value: 71.27713276123171 - task: type: PairClassification dataset: type: mteb/twitterurlcorpus-pairclassification name: MTEB TwitterURLCorpus config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 89.09457833663213 - type: cos_sim_ap value: 86.33024314706873 - type: cos_sim_f1 value: 78.59623733719248 - type: cos_sim_precision value: 74.13322413322413 - type: cos_sim_recall value: 83.63104404065291 - type: dot_accuracy value: 88.3086894089339 - type: dot_ap value: 83.92225241805097 - type: dot_f1 value: 76.8721826377781 - type: dot_precision value: 72.8168044077135 - type: dot_recall value: 81.40591315060055 - type: euclidean_accuracy value: 88.77052043311213 - type: euclidean_ap value: 85.7410710218755 - type: euclidean_f1 value: 77.97705489398781 - type: euclidean_precision value: 73.77713657598241 - type: euclidean_recall value: 82.68401601478288 - type: manhattan_accuracy value: 88.73753250281368 - type: manhattan_ap value: 85.72867199072802 - type: manhattan_f1 value: 77.89774182922812 - type: manhattan_precision value: 74.23787931635857 - type: manhattan_recall value: 81.93717277486911 - type: max_accuracy value: 89.09457833663213 - type: max_ap value: 86.33024314706873 - type: max_f1 value: 78.59623733719248 license: mit language: - en --- # [Universal AnglE Embedding](https://github.com/SeanLee97/AnglE) 📢 `WhereIsAI/UAE-Large-V1` **is licensed under MIT. Feel free to use it in any scenario.** If you use it for academic papers, we would greatly appreciate it if you could cite us. 👉 [citation info](#citation). **🤝 Follow us on:** - GitHub: https://github.com/SeanLee97/AnglE. - Arxiv: https://arxiv.org/abs/2309.12871 - 📘 Document: https://angle.readthedocs.io/en/latest/index.html Welcome to using AnglE to train and infer powerful sentence embeddings. **🏆 Achievements** - 📅 May 16, 2024 | AnglE's paper is accepted by ACL 2024 Main Conference - 📅 Dec 4, 2024 | 🔥 Our universal English sentence embedding `WhereIsAI/UAE-Large-V1` achieves **SOTA** on the [MTEB Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) with an average score of 64.64!  **🧑‍🤝‍🧑 Siblings:** - [WhereIsAI/UAE-Code-Large-V1](https://huggingface.co/WhereIsAI/UAE-Code-Large-V1): This model can be used for code or GitHub issue similarity measurement. # Usage ## 1. angle_emb ```bash python -m pip install -U angle-emb ``` 1) Non-Retrieval Tasks There is no need to specify any prompts. ```python from angle_emb import AnglE from scipy import spatial angle = AnglE.from_pretrained('WhereIsAI/UAE-Large-V1', pooling_strategy='cls').cuda() doc_vecs = angle.encode([ 'The weather is great!', 'The weather is very good!', 'i am going to bed' ]) for i, dv1 in enumerate(doc_vecs): for dv2 in doc_vecs[i+1:]: print(1 - spatial.distance.cosine(dv1, dv2)) ``` 2) Retrieval Tasks For retrieval purposes, please use the prompt `Prompts.C` for query (not for document). ```python from angle_emb import AnglE, Prompts from scipy import spatial angle = AnglE.from_pretrained('WhereIsAI/UAE-Large-V1', pooling_strategy='cls').cuda() qv = angle.encode(Prompts.C.format(text='what is the weather?')) doc_vecs = angle.encode([ 'The weather is great!', 'it is rainy today.', 'i am going to bed' ]) for dv in doc_vecs: print(1 - spatial.distance.cosine(qv[0], dv)) ``` ## 2. sentence transformer ```python from angle_emb import Prompts from sentence_transformers import SentenceTransformer model = SentenceTransformer("WhereIsAI/UAE-Large-V1").cuda() qv = model.encode(Prompts.C.format(text='what is the weather?')) doc_vecs = model.encode([ 'The weather is great!', 'it is rainy today.', 'i am going to bed' ]) for dv in doc_vecs: print(1 - spatial.distance.cosine(qv, dv)) ``` # Citation If you use our pre-trained models, welcome to support us by citing our work: ``` @article{li2023angle, title={AnglE-optimized Text Embeddings}, author={Li, Xianming and Li, Jing}, journal={arXiv preprint arXiv:2309.12871}, year={2023} } ```

Helsinki-NLP/opus-mt-es-en

Helsinki-NLP

transformers

translation

--- language: - es - en tags: - translation license: apache-2.0 --- ### spa-eng * source group: Spanish * target group: English * OPUS readme: [spa-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/spa-eng/README.md) * model: transformer * source language(s): spa * target language(s): eng * model: transformer * pre-processing: normalization + SentencePiece (spm32k,spm32k) * download original weights: [opus-2020-08-18.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.zip) * test set translations: [opus-2020-08-18.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.test.txt) * test set scores: [opus-2020-08-18.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.eval.txt) ## Benchmarks | testset | BLEU | chr-F | |-----------------------|-------|-------| | newssyscomb2009-spaeng.spa.eng | 30.6 | 0.570 | | news-test2008-spaeng.spa.eng | 27.9 | 0.553 | | newstest2009-spaeng.spa.eng | 30.4 | 0.572 | | newstest2010-spaeng.spa.eng | 36.1 | 0.614 | | newstest2011-spaeng.spa.eng | 34.2 | 0.599 | | newstest2012-spaeng.spa.eng | 37.9 | 0.624 | | newstest2013-spaeng.spa.eng | 35.3 | 0.609 | | Tatoeba-test.spa.eng | 59.6 | 0.739 | ### System Info: - hf_name: spa-eng - source_languages: spa - target_languages: eng - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/spa-eng/README.md - original_repo: Tatoeba-Challenge - tags: ['translation'] - languages: ['es', 'en'] - src_constituents: {'spa'} - tgt_constituents: {'eng'} - src_multilingual: False - tgt_multilingual: False - prepro: normalization + SentencePiece (spm32k,spm32k) - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.zip - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.test.txt - src_alpha3: spa - tgt_alpha3: eng - short_pair: es-en - chrF2_score: 0.7390000000000001 - bleu: 59.6 - brevity_penalty: 0.9740000000000001 - ref_len: 79376.0 - src_name: Spanish - tgt_name: English - train_date: 2020-08-18 00:00:00 - src_alpha2: es - tgt_alpha2: en - prefer_old: False - long_pair: spa-eng - helsinki_git_sha: d2f0910c89026c34a44e331e785dec1e0faa7b82 - transformers_git_sha: f7af09b4524b784d67ae8526f0e2fcc6f5ed0de9 - port_machine: brutasse - port_time: 2020-08-24-18:20

j-hartmann/emotion-english-distilroberta-base

j-hartmann

transformers

text-classification

--- language: "en" tags: - distilroberta - sentiment - emotion - twitter - reddit widget: - text: "Oh wow. I didn't know that." - text: "This movie always makes me cry.." - text: "Oh Happy Day" --- # Emotion English DistilRoBERTa-base # Description ℹ With this model, you can classify emotions in English text data. The model was trained on 6 diverse datasets (see Appendix below) and predicts Ekman's 6 basic emotions, plus a neutral class: 1) anger 🤬 2) disgust 🤢 3) fear 😨 4) joy 😀 5) neutral 😐 6) sadness 😭 7) surprise 😲 The model is a fine-tuned checkpoint of [DistilRoBERTa-base](https://huggingface.co/distilroberta-base). For a 'non-distilled' emotion model, please refer to the model card of the [RoBERTa-large](https://huggingface.co/j-hartmann/emotion-english-roberta-large) version. # Application 🚀 a) Run emotion model with 3 lines of code on single text example using Hugging Face's pipeline command on Google Colab: [](https://colab.research.google.com/github/j-hartmann/emotion-english-distilroberta-base/blob/main/simple_emotion_pipeline.ipynb) ```python from transformers import pipeline classifier = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", return_all_scores=True) classifier("I love this!") ``` ```python Output: [[{'label': 'anger', 'score': 0.004419783595949411}, {'label': 'disgust', 'score': 0.0016119900392368436}, {'label': 'fear', 'score': 0.0004138521908316761}, {'label': 'joy', 'score': 0.9771687984466553}, {'label': 'neutral', 'score': 0.005764586851000786}, {'label': 'sadness', 'score': 0.002092392183840275}, {'label': 'surprise', 'score': 0.008528684265911579}]] ``` b) Run emotion model on multiple examples and full datasets (e.g., .csv files) on Google Colab: [](https://colab.research.google.com/github/j-hartmann/emotion-english-distilroberta-base/blob/main/emotion_prediction_example.ipynb) # Contact 💻 Please reach out to [jochen.hartmann@tum.de](mailto:jochen.hartmann@tum.de) if you have any questions or feedback. Thanks to Samuel Domdey and [chrsiebert](https://huggingface.co/siebert) for their support in making this model available. # Reference ✅ For attribution, please cite the following reference if you use this model. A working paper will be available soon. ``` Jochen Hartmann, "Emotion English DistilRoBERTa-base". https://huggingface.co/j-hartmann/emotion-english-distilroberta-base/, 2022. ``` BibTex citation: ``` @misc{hartmann2022emotionenglish, author={Hartmann, Jochen}, title={Emotion English DistilRoBERTa-base}, year={2022}, howpublished = {\url{https://huggingface.co/j-hartmann/emotion-english-distilroberta-base/}}, } ``` # Appendix 📚 Please find an overview of the datasets used for training below. All datasets contain English text. The table summarizes which emotions are available in each of the datasets. The datasets represent a diverse collection of text types. Specifically, they contain emotion labels for texts from Twitter, Reddit, student self-reports, and utterances from TV dialogues. As MELD (Multimodal EmotionLines Dataset) extends the popular EmotionLines dataset, EmotionLines itself is not included here. |Name|anger|disgust|fear|joy|neutral|sadness|surprise| |---|---|---|---|---|---|---|---| |Crowdflower (2016)|Yes|-|-|Yes|Yes|Yes|Yes| |Emotion Dataset, Elvis et al. (2018)|Yes|-|Yes|Yes|-|Yes|Yes| |GoEmotions, Demszky et al. (2020)|Yes|Yes|Yes|Yes|Yes|Yes|Yes| |ISEAR, Vikash (2018)|Yes|Yes|Yes|Yes|-|Yes|-| |MELD, Poria et al. (2019)|Yes|Yes|Yes|Yes|Yes|Yes|Yes| |SemEval-2018, EI-reg, Mohammad et al. (2018) |Yes|-|Yes|Yes|-|Yes|-| The model is trained on a balanced subset from the datasets listed above (2,811 observations per emotion, i.e., nearly 20k observations in total). 80% of this balanced subset is used for training and 20% for evaluation. The evaluation accuracy is 66% (vs. the random-chance baseline of 1/7 = 14%). # Scientific Applications 📖 Below you can find a list of papers using "Emotion English DistilRoBERTa-base". If you would like your paper to be added to the list, please send me an email. - Butt, S., Sharma, S., Sharma, R., Sidorov, G., & Gelbukh, A. (2022). What goes on inside rumour and non-rumour tweets and their reactions: A Psycholinguistic Analyses. Computers in Human Behavior, 107345. - Kuang, Z., Zong, S., Zhang, J., Chen, J., & Liu, H. (2022). Music-to-Text Synaesthesia: Generating Descriptive Text from Music Recordings. arXiv preprint arXiv:2210.00434. - Rozado, D., Hughes, R., & Halberstadt, J. (2022). Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models. Plos one, 17(10), e0276367.

intfloat/multilingual-e5-base

intfloat

sentence-transformers

sentence-similarity

--- tags: - mteb - Sentence Transformers - sentence-similarity - sentence-transformers model-index: - name: multilingual-e5-base results: - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (en) config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 78.97014925373135 - type: ap value: 43.69351129103008 - type: f1 value: 73.38075030070492 - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (de) config: de split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 71.7237687366167 - type: ap value: 82.22089859962671 - type: f1 value: 69.95532758884401 - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (en-ext) config: en-ext split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 79.65517241379312 - type: ap value: 28.507918657094738 - type: f1 value: 66.84516013726119 - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (ja) config: ja split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 73.32976445396146 - type: ap value: 20.720481637566014 - type: f1 value: 59.78002763416003 - task: type: Classification dataset: type: mteb/amazon_polarity name: MTEB AmazonPolarityClassification config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 90.63775 - type: ap value: 87.22277903861716 - type: f1 value: 90.60378636386807 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (en) config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 44.546 - type: f1 value: 44.05666638370923 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (de) config: de split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 41.828 - type: f1 value: 41.2710255644252 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (es) config: es split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 40.534 - type: f1 value: 39.820743174270326 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (fr) config: fr split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 39.684 - type: f1 value: 39.11052682815307 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (ja) config: ja split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 37.436 - type: f1 value: 37.07082931930871 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (zh) config: zh split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 37.226000000000006 - type: f1 value: 36.65372077739185 - task: type: Retrieval dataset: type: arguana name: MTEB ArguAna config: default split: test revision: None metrics: - type: map_at_1 value: 22.831000000000003 - type: map_at_10 value: 36.42 - type: map_at_100 value: 37.699 - type: map_at_1000 value: 37.724000000000004 - type: map_at_3 value: 32.207 - type: map_at_5 value: 34.312 - type: mrr_at_1 value: 23.257 - type: mrr_at_10 value: 36.574 - type: mrr_at_100 value: 37.854 - type: mrr_at_1000 value: 37.878 - type: mrr_at_3 value: 32.385000000000005 - type: mrr_at_5 value: 34.48 - type: ndcg_at_1 value: 22.831000000000003 - type: ndcg_at_10 value: 44.230000000000004 - type: ndcg_at_100 value: 49.974000000000004 - type: ndcg_at_1000 value: 50.522999999999996 - type: ndcg_at_3 value: 35.363 - type: ndcg_at_5 value: 39.164 - type: precision_at_1 value: 22.831000000000003 - type: precision_at_10 value: 6.935 - type: precision_at_100 value: 0.9520000000000001 - type: precision_at_1000 value: 0.099 - type: precision_at_3 value: 14.841 - type: precision_at_5 value: 10.754 - type: recall_at_1 value: 22.831000000000003 - type: recall_at_10 value: 69.346 - type: recall_at_100 value: 95.235 - type: recall_at_1000 value: 99.36 - type: recall_at_3 value: 44.523 - type: recall_at_5 value: 53.769999999999996 - task: type: Clustering dataset: type: mteb/arxiv-clustering-p2p name: MTEB ArxivClusteringP2P config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 40.27789869854063 - task: type: Clustering dataset: type: mteb/arxiv-clustering-s2s name: MTEB ArxivClusteringS2S config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 35.41979463347428 - task: type: Reranking dataset: type: mteb/askubuntudupquestions-reranking name: MTEB AskUbuntuDupQuestions config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 58.22752045109304 - type: mrr value: 71.51112430198303 - task: type: STS dataset: type: mteb/biosses-sts name: MTEB BIOSSES config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 84.71147646622866 - type: cos_sim_spearman value: 85.059167046486 - type: euclidean_pearson value: 75.88421613600647 - type: euclidean_spearman value: 75.12821787150585 - type: manhattan_pearson value: 75.22005646957604 - type: manhattan_spearman value: 74.42880434453272 - task: type: BitextMining dataset: type: mteb/bucc-bitext-mining name: MTEB BUCC (de-en) config: de-en split: test revision: d51519689f32196a32af33b075a01d0e7c51e252 metrics: - type: accuracy value: 99.23799582463465 - type: f1 value: 99.12665274878218 - type: precision value: 99.07098121085595 - type: recall value: 99.23799582463465 - task: type: BitextMining dataset: type: mteb/bucc-bitext-mining name: MTEB BUCC (fr-en) config: fr-en split: test revision: d51519689f32196a32af33b075a01d0e7c51e252 metrics: - type: accuracy value: 97.88685890380806 - type: f1 value: 97.59336708489249 - type: precision value: 97.44662117543473 - type: recall value: 97.88685890380806 - task: type: BitextMining dataset: type: mteb/bucc-bitext-mining name: MTEB BUCC (ru-en) config: ru-en split: test revision: d51519689f32196a32af33b075a01d0e7c51e252 metrics: - type: accuracy value: 97.47142362313821 - type: f1 value: 97.1989377670015 - type: precision value: 97.06384944001847 - type: recall value: 97.47142362313821 - task: type: BitextMining dataset: type: mteb/bucc-bitext-mining name: MTEB BUCC (zh-en) config: zh-en split: test revision: d51519689f32196a32af33b075a01d0e7c51e252 metrics: - type: accuracy value: 98.4728804634018 - type: f1 value: 98.2973494821836 - type: precision value: 98.2095839915745 - type: recall value: 98.4728804634018 - task: type: Classification dataset: type: mteb/banking77 name: MTEB Banking77Classification config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 82.74025974025975 - type: f1 value: 82.67420447730439 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-p2p name: MTEB BiorxivClusteringP2P config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 35.0380848063507 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-s2s name: MTEB BiorxivClusteringS2S config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 29.45956405670166 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackAndroidRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 32.122 - type: map_at_10 value: 42.03 - type: map_at_100 value: 43.364000000000004 - type: map_at_1000 value: 43.474000000000004 - type: map_at_3 value: 38.804 - type: map_at_5 value: 40.585 - type: mrr_at_1 value: 39.914 - type: mrr_at_10 value: 48.227 - type: mrr_at_100 value: 49.018 - type: mrr_at_1000 value: 49.064 - type: mrr_at_3 value: 45.994 - type: mrr_at_5 value: 47.396 - type: ndcg_at_1 value: 39.914 - type: ndcg_at_10 value: 47.825 - type: ndcg_at_100 value: 52.852 - type: ndcg_at_1000 value: 54.891 - type: ndcg_at_3 value: 43.517 - type: ndcg_at_5 value: 45.493 - type: precision_at_1 value: 39.914 - type: precision_at_10 value: 8.956 - type: precision_at_100 value: 1.388 - type: precision_at_1000 value: 0.182 - type: precision_at_3 value: 20.791999999999998 - type: precision_at_5 value: 14.821000000000002 - type: recall_at_1 value: 32.122 - type: recall_at_10 value: 58.294999999999995 - type: recall_at_100 value: 79.726 - type: recall_at_1000 value: 93.099 - type: recall_at_3 value: 45.017 - type: recall_at_5 value: 51.002 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackEnglishRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 29.677999999999997 - type: map_at_10 value: 38.684000000000005 - type: map_at_100 value: 39.812999999999995 - type: map_at_1000 value: 39.945 - type: map_at_3 value: 35.831 - type: map_at_5 value: 37.446 - type: mrr_at_1 value: 37.771 - type: mrr_at_10 value: 44.936 - type: mrr_at_100 value: 45.583 - type: mrr_at_1000 value: 45.634 - type: mrr_at_3 value: 42.771 - type: mrr_at_5 value: 43.994 - type: ndcg_at_1 value: 37.771 - type: ndcg_at_10 value: 44.059 - type: ndcg_at_100 value: 48.192 - type: ndcg_at_1000 value: 50.375 - type: ndcg_at_3 value: 40.172000000000004 - type: ndcg_at_5 value: 41.899 - type: precision_at_1 value: 37.771 - type: precision_at_10 value: 8.286999999999999 - type: precision_at_100 value: 1.322 - type: precision_at_1000 value: 0.178 - type: precision_at_3 value: 19.406000000000002 - type: precision_at_5 value: 13.745 - type: recall_at_1 value: 29.677999999999997 - type: recall_at_10 value: 53.071 - type: recall_at_100 value: 70.812 - type: recall_at_1000 value: 84.841 - type: recall_at_3 value: 41.016000000000005 - type: recall_at_5 value: 46.22 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGamingRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 42.675000000000004 - type: map_at_10 value: 53.93599999999999 - type: map_at_100 value: 54.806999999999995 - type: map_at_1000 value: 54.867 - type: map_at_3 value: 50.934000000000005 - type: map_at_5 value: 52.583 - type: mrr_at_1 value: 48.339 - type: mrr_at_10 value: 57.265 - type: mrr_at_100 value: 57.873 - type: mrr_at_1000 value: 57.906 - type: mrr_at_3 value: 55.193000000000005 - type: mrr_at_5 value: 56.303000000000004 - type: ndcg_at_1 value: 48.339 - type: ndcg_at_10 value: 59.19799999999999 - type: ndcg_at_100 value: 62.743 - type: ndcg_at_1000 value: 63.99399999999999 - type: ndcg_at_3 value: 54.367 - type: ndcg_at_5 value: 56.548 - type: precision_at_1 value: 48.339 - type: precision_at_10 value: 9.216000000000001 - type: precision_at_100 value: 1.1809999999999998 - type: precision_at_1000 value: 0.134 - type: precision_at_3 value: 23.72 - type: precision_at_5 value: 16.025 - type: recall_at_1 value: 42.675000000000004 - type: recall_at_10 value: 71.437 - type: recall_at_100 value: 86.803 - type: recall_at_1000 value: 95.581 - type: recall_at_3 value: 58.434 - type: recall_at_5 value: 63.754 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGisRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 23.518 - type: map_at_10 value: 30.648999999999997 - type: map_at_100 value: 31.508999999999997 - type: map_at_1000 value: 31.604 - type: map_at_3 value: 28.247 - type: map_at_5 value: 29.65 - type: mrr_at_1 value: 25.650000000000002 - type: mrr_at_10 value: 32.771 - type: mrr_at_100 value: 33.554 - type: mrr_at_1000 value: 33.629999999999995 - type: mrr_at_3 value: 30.433 - type: mrr_at_5 value: 31.812 - type: ndcg_at_1 value: 25.650000000000002 - type: ndcg_at_10 value: 34.929 - type: ndcg_at_100 value: 39.382 - type: ndcg_at_1000 value: 41.913 - type: ndcg_at_3 value: 30.292 - type: ndcg_at_5 value: 32.629999999999995 - type: precision_at_1 value: 25.650000000000002 - type: precision_at_10 value: 5.311 - type: precision_at_100 value: 0.792 - type: precision_at_1000 value: 0.105 - type: precision_at_3 value: 12.58 - type: precision_at_5 value: 8.994 - type: recall_at_1 value: 23.518 - type: recall_at_10 value: 46.19 - type: recall_at_100 value: 67.123 - type: recall_at_1000 value: 86.442 - type: recall_at_3 value: 33.678000000000004 - type: recall_at_5 value: 39.244 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackMathematicaRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 15.891 - type: map_at_10 value: 22.464000000000002 - type: map_at_100 value: 23.483 - type: map_at_1000 value: 23.613 - type: map_at_3 value: 20.080000000000002 - type: map_at_5 value: 21.526 - type: mrr_at_1 value: 20.025000000000002 - type: mrr_at_10 value: 26.712999999999997 - type: mrr_at_100 value: 27.650000000000002 - type: mrr_at_1000 value: 27.737000000000002 - type: mrr_at_3 value: 24.274 - type: mrr_at_5 value: 25.711000000000002 - type: ndcg_at_1 value: 20.025000000000002 - type: ndcg_at_10 value: 27.028999999999996 - type: ndcg_at_100 value: 32.064 - type: ndcg_at_1000 value: 35.188 - type: ndcg_at_3 value: 22.512999999999998 - type: ndcg_at_5 value: 24.89 - type: precision_at_1 value: 20.025000000000002 - type: precision_at_10 value: 4.776 - type: precision_at_100 value: 0.8500000000000001 - type: precision_at_1000 value: 0.125 - type: precision_at_3 value: 10.531 - type: precision_at_5 value: 7.811 - type: recall_at_1 value: 15.891 - type: recall_at_10 value: 37.261 - type: recall_at_100 value: 59.12 - type: recall_at_1000 value: 81.356 - type: recall_at_3 value: 24.741 - type: recall_at_5 value: 30.753999999999998 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackPhysicsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 27.544 - type: map_at_10 value: 36.283 - type: map_at_100 value: 37.467 - type: map_at_1000 value: 37.574000000000005 - type: map_at_3 value: 33.528999999999996 - type: map_at_5 value: 35.028999999999996 - type: mrr_at_1 value: 34.166999999999994 - type: mrr_at_10 value: 41.866 - type: mrr_at_100 value: 42.666 - type: mrr_at_1000 value: 42.716 - type: mrr_at_3 value: 39.541 - type: mrr_at_5 value: 40.768 - type: ndcg_at_1 value: 34.166999999999994 - type: ndcg_at_10 value: 41.577 - type: ndcg_at_100 value: 46.687 - type: ndcg_at_1000 value: 48.967 - type: ndcg_at_3 value: 37.177 - type: ndcg_at_5 value: 39.097 - type: precision_at_1 value: 34.166999999999994 - type: precision_at_10 value: 7.420999999999999 - type: precision_at_100 value: 1.165 - type: precision_at_1000 value: 0.154 - type: precision_at_3 value: 17.291999999999998 - type: precision_at_5 value: 12.166 - type: recall_at_1 value: 27.544 - type: recall_at_10 value: 51.99399999999999 - type: recall_at_100 value: 73.738 - type: recall_at_1000 value: 89.33 - type: recall_at_3 value: 39.179 - type: recall_at_5 value: 44.385999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackProgrammersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 26.661 - type: map_at_10 value: 35.475 - type: map_at_100 value: 36.626999999999995 - type: map_at_1000 value: 36.741 - type: map_at_3 value: 32.818000000000005 - type: map_at_5 value: 34.397 - type: mrr_at_1 value: 32.647999999999996 - type: mrr_at_10 value: 40.784 - type: mrr_at_100 value: 41.602 - type: mrr_at_1000 value: 41.661 - type: mrr_at_3 value: 38.68 - type: mrr_at_5 value: 39.838 - type: ndcg_at_1 value: 32.647999999999996 - type: ndcg_at_10 value: 40.697 - type: ndcg_at_100 value: 45.799 - type: ndcg_at_1000 value: 48.235 - type: ndcg_at_3 value: 36.516 - type: ndcg_at_5 value: 38.515 - type: precision_at_1 value: 32.647999999999996 - type: precision_at_10 value: 7.202999999999999 - type: precision_at_100 value: 1.1360000000000001 - type: precision_at_1000 value: 0.151 - type: precision_at_3 value: 17.314 - type: precision_at_5 value: 12.145999999999999 - type: recall_at_1 value: 26.661 - type: recall_at_10 value: 50.995000000000005 - type: recall_at_100 value: 73.065 - type: recall_at_1000 value: 89.781 - type: recall_at_3 value: 39.073 - type: recall_at_5 value: 44.395 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.946583333333333 - type: map_at_10 value: 33.79725 - type: map_at_100 value: 34.86408333333333 - type: map_at_1000 value: 34.9795 - type: map_at_3 value: 31.259999999999998 - type: map_at_5 value: 32.71541666666666 - type: mrr_at_1 value: 30.863749999999996 - type: mrr_at_10 value: 37.99183333333333 - type: mrr_at_100 value: 38.790499999999994 - type: mrr_at_1000 value: 38.85575000000001 - type: mrr_at_3 value: 35.82083333333333 - type: mrr_at_5 value: 37.07533333333333 - type: ndcg_at_1 value: 30.863749999999996 - type: ndcg_at_10 value: 38.52141666666667 - type: ndcg_at_100 value: 43.17966666666667 - type: ndcg_at_1000 value: 45.64608333333333 - type: ndcg_at_3 value: 34.333000000000006 - type: ndcg_at_5 value: 36.34975 - type: precision_at_1 value: 30.863749999999996 - type: precision_at_10 value: 6.598999999999999 - type: precision_at_100 value: 1.0502500000000001 - type: precision_at_1000 value: 0.14400000000000002 - type: precision_at_3 value: 15.557583333333334 - type: precision_at_5 value: 11.020000000000001 - type: recall_at_1 value: 25.946583333333333 - type: recall_at_10 value: 48.36991666666666 - type: recall_at_100 value: 69.02408333333334 - type: recall_at_1000 value: 86.43858333333331 - type: recall_at_3 value: 36.4965 - type: recall_at_5 value: 41.76258333333334 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackStatsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 22.431 - type: map_at_10 value: 28.889 - type: map_at_100 value: 29.642000000000003 - type: map_at_1000 value: 29.742 - type: map_at_3 value: 26.998 - type: map_at_5 value: 28.172000000000004 - type: mrr_at_1 value: 25.307000000000002 - type: mrr_at_10 value: 31.763 - type: mrr_at_100 value: 32.443 - type: mrr_at_1000 value: 32.531 - type: mrr_at_3 value: 29.959000000000003 - type: mrr_at_5 value: 31.063000000000002 - type: ndcg_at_1 value: 25.307000000000002 - type: ndcg_at_10 value: 32.586999999999996 - type: ndcg_at_100 value: 36.5 - type: ndcg_at_1000 value: 39.133 - type: ndcg_at_3 value: 29.25 - type: ndcg_at_5 value: 31.023 - type: precision_at_1 value: 25.307000000000002 - type: precision_at_10 value: 4.954 - type: precision_at_100 value: 0.747 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 12.577 - type: precision_at_5 value: 8.741999999999999 - type: recall_at_1 value: 22.431 - type: recall_at_10 value: 41.134 - type: recall_at_100 value: 59.28600000000001 - type: recall_at_1000 value: 78.857 - type: recall_at_3 value: 31.926 - type: recall_at_5 value: 36.335 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackTexRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 17.586 - type: map_at_10 value: 23.304 - type: map_at_100 value: 24.159 - type: map_at_1000 value: 24.281 - type: map_at_3 value: 21.316 - type: map_at_5 value: 22.383 - type: mrr_at_1 value: 21.645 - type: mrr_at_10 value: 27.365000000000002 - type: mrr_at_100 value: 28.108 - type: mrr_at_1000 value: 28.192 - type: mrr_at_3 value: 25.482 - type: mrr_at_5 value: 26.479999999999997 - type: ndcg_at_1 value: 21.645 - type: ndcg_at_10 value: 27.306 - type: ndcg_at_100 value: 31.496000000000002 - type: ndcg_at_1000 value: 34.53 - type: ndcg_at_3 value: 23.73 - type: ndcg_at_5 value: 25.294 - type: precision_at_1 value: 21.645 - type: precision_at_10 value: 4.797 - type: precision_at_100 value: 0.8059999999999999 - type: precision_at_1000 value: 0.121 - type: precision_at_3 value: 10.850999999999999 - type: precision_at_5 value: 7.736 - type: recall_at_1 value: 17.586 - type: recall_at_10 value: 35.481 - type: recall_at_100 value: 54.534000000000006 - type: recall_at_1000 value: 76.456 - type: recall_at_3 value: 25.335 - type: recall_at_5 value: 29.473 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackUnixRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.095 - type: map_at_10 value: 32.374 - type: map_at_100 value: 33.537 - type: map_at_1000 value: 33.634 - type: map_at_3 value: 30.089 - type: map_at_5 value: 31.433 - type: mrr_at_1 value: 29.198 - type: mrr_at_10 value: 36.01 - type: mrr_at_100 value: 37.022 - type: mrr_at_1000 value: 37.083 - type: mrr_at_3 value: 33.94 - type: mrr_at_5 value: 35.148 - type: ndcg_at_1 value: 29.198 - type: ndcg_at_10 value: 36.729 - type: ndcg_at_100 value: 42.114000000000004 - type: ndcg_at_1000 value: 44.592 - type: ndcg_at_3 value: 32.644 - type: ndcg_at_5 value: 34.652 - type: precision_at_1 value: 29.198 - type: precision_at_10 value: 5.970000000000001 - type: precision_at_100 value: 0.967 - type: precision_at_1000 value: 0.129 - type: precision_at_3 value: 14.396999999999998 - type: precision_at_5 value: 10.093 - type: recall_at_1 value: 25.095 - type: recall_at_10 value: 46.392 - type: recall_at_100 value: 69.706 - type: recall_at_1000 value: 87.738 - type: recall_at_3 value: 35.303000000000004 - type: recall_at_5 value: 40.441 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWebmastersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 26.857999999999997 - type: map_at_10 value: 34.066 - type: map_at_100 value: 35.671 - type: map_at_1000 value: 35.881 - type: map_at_3 value: 31.304 - type: map_at_5 value: 32.885 - type: mrr_at_1 value: 32.411 - type: mrr_at_10 value: 38.987 - type: mrr_at_100 value: 39.894 - type: mrr_at_1000 value: 39.959 - type: mrr_at_3 value: 36.626999999999995 - type: mrr_at_5 value: 38.011 - type: ndcg_at_1 value: 32.411 - type: ndcg_at_10 value: 39.208 - type: ndcg_at_100 value: 44.626 - type: ndcg_at_1000 value: 47.43 - type: ndcg_at_3 value: 35.091 - type: ndcg_at_5 value: 37.119 - type: precision_at_1 value: 32.411 - type: precision_at_10 value: 7.51 - type: precision_at_100 value: 1.486 - type: precision_at_1000 value: 0.234 - type: precision_at_3 value: 16.14 - type: precision_at_5 value: 11.976 - type: recall_at_1 value: 26.857999999999997 - type: recall_at_10 value: 47.407 - type: recall_at_100 value: 72.236 - type: recall_at_1000 value: 90.77 - type: recall_at_3 value: 35.125 - type: recall_at_5 value: 40.522999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWordpressRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 21.3 - type: map_at_10 value: 27.412999999999997 - type: map_at_100 value: 28.29 - type: map_at_1000 value: 28.398 - type: map_at_3 value: 25.169999999999998 - type: map_at_5 value: 26.496 - type: mrr_at_1 value: 23.29 - type: mrr_at_10 value: 29.215000000000003 - type: mrr_at_100 value: 30.073 - type: mrr_at_1000 value: 30.156 - type: mrr_at_3 value: 26.956000000000003 - type: mrr_at_5 value: 28.38 - type: ndcg_at_1 value: 23.29 - type: ndcg_at_10 value: 31.113000000000003 - type: ndcg_at_100 value: 35.701 - type: ndcg_at_1000 value: 38.505 - type: ndcg_at_3 value: 26.727 - type: ndcg_at_5 value: 29.037000000000003 - type: precision_at_1 value: 23.29 - type: precision_at_10 value: 4.787 - type: precision_at_100 value: 0.763 - type: precision_at_1000 value: 0.11100000000000002 - type: precision_at_3 value: 11.091 - type: precision_at_5 value: 7.985 - type: recall_at_1 value: 21.3 - type: recall_at_10 value: 40.782000000000004 - type: recall_at_100 value: 62.13999999999999 - type: recall_at_1000 value: 83.012 - type: recall_at_3 value: 29.131 - type: recall_at_5 value: 34.624 - task: type: Retrieval dataset: type: climate-fever name: MTEB ClimateFEVER config: default split: test revision: None metrics: - type: map_at_1 value: 9.631 - type: map_at_10 value: 16.634999999999998 - type: map_at_100 value: 18.23 - type: map_at_1000 value: 18.419 - type: map_at_3 value: 13.66 - type: map_at_5 value: 15.173 - type: mrr_at_1 value: 21.368000000000002 - type: mrr_at_10 value: 31.56 - type: mrr_at_100 value: 32.58 - type: mrr_at_1000 value: 32.633 - type: mrr_at_3 value: 28.241 - type: mrr_at_5 value: 30.225 - type: ndcg_at_1 value: 21.368000000000002 - type: ndcg_at_10 value: 23.855999999999998 - type: ndcg_at_100 value: 30.686999999999998 - type: ndcg_at_1000 value: 34.327000000000005 - type: ndcg_at_3 value: 18.781 - type: ndcg_at_5 value: 20.73 - type: precision_at_1 value: 21.368000000000002 - type: precision_at_10 value: 7.564 - type: precision_at_100 value: 1.496 - type: precision_at_1000 value: 0.217 - type: precision_at_3 value: 13.876 - type: precision_at_5 value: 11.062 - type: recall_at_1 value: 9.631 - type: recall_at_10 value: 29.517 - type: recall_at_100 value: 53.452 - type: recall_at_1000 value: 74.115 - type: recall_at_3 value: 17.605999999999998 - type: recall_at_5 value: 22.505 - task: type: Retrieval dataset: type: dbpedia-entity name: MTEB DBPedia config: default split: test revision: None metrics: - type: map_at_1 value: 8.885 - type: map_at_10 value: 18.798000000000002 - type: map_at_100 value: 26.316 - type: map_at_1000 value: 27.869 - type: map_at_3 value: 13.719000000000001 - type: map_at_5 value: 15.716 - type: mrr_at_1 value: 66 - type: mrr_at_10 value: 74.263 - type: mrr_at_100 value: 74.519 - type: mrr_at_1000 value: 74.531 - type: mrr_at_3 value: 72.458 - type: mrr_at_5 value: 73.321 - type: ndcg_at_1 value: 53.87499999999999 - type: ndcg_at_10 value: 40.355999999999995 - type: ndcg_at_100 value: 44.366 - type: ndcg_at_1000 value: 51.771 - type: ndcg_at_3 value: 45.195 - type: ndcg_at_5 value: 42.187000000000005 - type: precision_at_1 value: 66 - type: precision_at_10 value: 31.75 - type: precision_at_100 value: 10.11 - type: precision_at_1000 value: 1.9800000000000002 - type: precision_at_3 value: 48.167 - type: precision_at_5 value: 40.050000000000004 - type: recall_at_1 value: 8.885 - type: recall_at_10 value: 24.471999999999998 - type: recall_at_100 value: 49.669000000000004 - type: recall_at_1000 value: 73.383 - type: recall_at_3 value: 14.872 - type: recall_at_5 value: 18.262999999999998 - task: type: Classification dataset: type: mteb/emotion name: MTEB EmotionClassification config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 45.18 - type: f1 value: 40.26878691789978 - task: type: Retrieval dataset: type: fever name: MTEB FEVER config: default split: test revision: None metrics: - type: map_at_1 value: 62.751999999999995 - type: map_at_10 value: 74.131 - type: map_at_100 value: 74.407 - type: map_at_1000 value: 74.423 - type: map_at_3 value: 72.329 - type: map_at_5 value: 73.555 - type: mrr_at_1 value: 67.282 - type: mrr_at_10 value: 78.292 - type: mrr_at_100 value: 78.455 - type: mrr_at_1000 value: 78.458 - type: mrr_at_3 value: 76.755 - type: mrr_at_5 value: 77.839 - type: ndcg_at_1 value: 67.282 - type: ndcg_at_10 value: 79.443 - type: ndcg_at_100 value: 80.529 - type: ndcg_at_1000 value: 80.812 - type: ndcg_at_3 value: 76.281 - type: ndcg_at_5 value: 78.235 - type: precision_at_1 value: 67.282 - type: precision_at_10 value: 10.078 - type: precision_at_100 value: 1.082 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 30.178 - type: precision_at_5 value: 19.232 - type: recall_at_1 value: 62.751999999999995 - type: recall_at_10 value: 91.521 - type: recall_at_100 value: 95.997 - type: recall_at_1000 value: 97.775 - type: recall_at_3 value: 83.131 - type: recall_at_5 value: 87.93299999999999 - task: type: Retrieval dataset: type: fiqa name: MTEB FiQA2018 config: default split: test revision: None metrics: - type: map_at_1 value: 18.861 - type: map_at_10 value: 30.252000000000002 - type: map_at_100 value: 32.082 - type: map_at_1000 value: 32.261 - type: map_at_3 value: 25.909 - type: map_at_5 value: 28.296 - type: mrr_at_1 value: 37.346000000000004 - type: mrr_at_10 value: 45.802 - type: mrr_at_100 value: 46.611999999999995 - type: mrr_at_1000 value: 46.659 - type: mrr_at_3 value: 43.056 - type: mrr_at_5 value: 44.637 - type: ndcg_at_1 value: 37.346000000000004 - type: ndcg_at_10 value: 38.169 - type: ndcg_at_100 value: 44.864 - type: ndcg_at_1000 value: 47.974 - type: ndcg_at_3 value: 33.619 - type: ndcg_at_5 value: 35.317 - type: precision_at_1 value: 37.346000000000004 - type: precision_at_10 value: 10.693999999999999 - type: precision_at_100 value: 1.775 - type: precision_at_1000 value: 0.231 - type: precision_at_3 value: 22.325 - type: precision_at_5 value: 16.852 - type: recall_at_1 value: 18.861 - type: recall_at_10 value: 45.672000000000004 - type: recall_at_100 value: 70.60499999999999 - type: recall_at_1000 value: 89.216 - type: recall_at_3 value: 30.361 - type: recall_at_5 value: 36.998999999999995 - task: type: Retrieval dataset: type: hotpotqa name: MTEB HotpotQA config: default split: test revision: None metrics: - type: map_at_1 value: 37.852999999999994 - type: map_at_10 value: 59.961 - type: map_at_100 value: 60.78 - type: map_at_1000 value: 60.843 - type: map_at_3 value: 56.39999999999999 - type: map_at_5 value: 58.646 - type: mrr_at_1 value: 75.70599999999999 - type: mrr_at_10 value: 82.321 - type: mrr_at_100 value: 82.516 - type: mrr_at_1000 value: 82.525 - type: mrr_at_3 value: 81.317 - type: mrr_at_5 value: 81.922 - type: ndcg_at_1 value: 75.70599999999999 - type: ndcg_at_10 value: 68.557 - type: ndcg_at_100 value: 71.485 - type: ndcg_at_1000 value: 72.71600000000001 - type: ndcg_at_3 value: 63.524 - type: ndcg_at_5 value: 66.338 - type: precision_at_1 value: 75.70599999999999 - type: precision_at_10 value: 14.463000000000001 - type: precision_at_100 value: 1.677 - type: precision_at_1000 value: 0.184 - type: precision_at_3 value: 40.806 - type: precision_at_5 value: 26.709 - type: recall_at_1 value: 37.852999999999994 - type: recall_at_10 value: 72.316 - type: recall_at_100 value: 83.842 - type: recall_at_1000 value: 91.999 - type: recall_at_3 value: 61.209 - type: recall_at_5 value: 66.77199999999999 - task: type: Classification dataset: type: mteb/imdb name: MTEB ImdbClassification config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 85.46039999999999 - type: ap value: 79.9812521351881 - type: f1 value: 85.31722909702084 - task: type: Retrieval dataset: type: msmarco name: MTEB MSMARCO config: default split: dev revision: None metrics: - type: map_at_1 value: 22.704 - type: map_at_10 value: 35.329 - type: map_at_100 value: 36.494 - type: map_at_1000 value: 36.541000000000004 - type: map_at_3 value: 31.476 - type: map_at_5 value: 33.731 - type: mrr_at_1 value: 23.294999999999998 - type: mrr_at_10 value: 35.859 - type: mrr_at_100 value: 36.968 - type: mrr_at_1000 value: 37.008 - type: mrr_at_3 value: 32.085 - type: mrr_at_5 value: 34.299 - type: ndcg_at_1 value: 23.324 - type: ndcg_at_10 value: 42.274 - type: ndcg_at_100 value: 47.839999999999996 - type: ndcg_at_1000 value: 48.971 - type: ndcg_at_3 value: 34.454 - type: ndcg_at_5 value: 38.464 - type: precision_at_1 value: 23.324 - type: precision_at_10 value: 6.648 - type: precision_at_100 value: 0.9440000000000001 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 14.674999999999999 - type: precision_at_5 value: 10.850999999999999 - type: recall_at_1 value: 22.704 - type: recall_at_10 value: 63.660000000000004 - type: recall_at_100 value: 89.29899999999999 - type: recall_at_1000 value: 97.88900000000001 - type: recall_at_3 value: 42.441 - type: recall_at_5 value: 52.04 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (en) config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 93.1326949384405 - type: f1 value: 92.89743579612082 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (de) config: de split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 89.62524654832347 - type: f1 value: 88.65106082263151 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (es) config: es split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 90.59039359573046 - type: f1 value: 90.31532892105662 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (fr) config: fr split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 86.21046038208581 - type: f1 value: 86.41459529813113 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (hi) config: hi split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 87.3180351380423 - type: f1 value: 86.71383078226444 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (th) config: th split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 86.24231464737792 - type: f1 value: 86.31845567592403 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (en) config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 75.27131782945736 - type: f1 value: 57.52079940417103 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (de) config: de split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 71.2341504649197 - type: f1 value: 51.349951558039244 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (es) config: es split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 71.27418278852569 - type: f1 value: 50.1714985749095 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (fr) config: fr split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 67.68243031631694 - type: f1 value: 50.1066160836192 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (hi) config: hi split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 69.2362854069559 - type: f1 value: 48.821279948766424 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (th) config: th split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 71.71428571428571 - type: f1 value: 53.94611389496195 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (af) config: af split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 59.97646267652992 - type: f1 value: 57.26797883561521 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (am) config: am split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 53.65501008742435 - type: f1 value: 50.416258382177034 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (ar) config: ar split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 57.45796906523201 - type: f1 value: 53.306690547422185 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (az) config: az split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 62.59246805648957 - type: f1 value: 59.818381969051494 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (bn) config: bn split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 61.126429051782104 - type: f1 value: 58.25993593933026 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (cy) config: cy split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 50.057162071284466 - type: f1 value: 46.96095728790911 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (da) config: da split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 66.64425016812375 - type: f1 value: 62.858291698755764 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (de) config: de split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 66.08944182918628 - type: f1 value: 62.44639030604241 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (el) config: el split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 64.68056489576328 - type: f1 value: 61.775326758789504 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (en) config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 72.11163416274377 - type: f1 value: 69.70789096927015 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (es) config: es split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 68.40282447881641 - type: f1 value: 66.38492065671895 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (fa) config: fa split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 67.24613315400134 - type: f1 value: 64.3348019501336 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (fi) config: fi split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 65.78345662407531 - type: f1 value: 62.21279452354622 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (fr) config: fr split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 67.9455279085407 - type: f1 value: 65.48193124964094 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (he) config: he split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 62.05110961667788 - type: f1 value: 58.097856564684534 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (hi) config: hi split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 64.95292535305985 - type: f1 value: 62.09182174767901 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (hu) config: hu split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 64.97310020174848 - type: f1 value: 61.14252567730396 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (hy) config: hy split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 60.08069939475453 - type: f1 value: 57.044041742492034 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (id) config: id split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 66.63752521856085 - type: f1 value: 63.889340907205316 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (is) config: is split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 56.385339609952936 - type: f1 value: 53.449033750088304 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (it) config: it split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 68.93073301950234 - type: f1 value: 65.9884357824104 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (ja) config: ja split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 68.94418291862812 - type: f1 value: 66.48740222583132 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (jv) config: jv split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 54.26025554808339 - type: f1 value: 50.19562815100793 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (ka) config: ka split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 48.98789509078682 - type: f1 value: 46.65788438676836 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (km) config: km split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 44.68728984532616 - type: f1 value: 41.642419349541996 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (kn) config: kn split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 59.19300605245461 - type: f1 value: 55.8626492442437 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (ko) config: ko split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 66.33826496301278 - type: f1 value: 63.89499791648792 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (lv) config: lv split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 60.33960995292536 - type: f1 value: 57.15242464180892 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (ml) config: ml split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 63.09347679892402 - type: f1 value: 59.64733214063841 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (mn) config: mn split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 58.75924680564896 - type: f1 value: 55.96585692366827 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (ms) config: ms split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 62.48486886348352 - type: f1 value: 59.45143559032946 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (my) config: my split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 58.56422326832549 - type: f1 value: 54.96368702901926 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (nb) config: nb split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 66.18022864828512 - type: f1 value: 63.05369805040634 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (nl) config: nl split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 67.30329522528581 - type: f1 value: 64.06084612020727 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (pl) config: pl split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 68.36919973100201 - type: f1 value: 65.12154124788887 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (pt) config: pt split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 68.98117014122394 - type: f1 value: 66.41847559806962 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (ro) config: ro split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 65.53799596503026 - type: f1 value: 62.17067330740817 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (ru) config: ru split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 69.01815736381977 - type: f1 value: 66.24988369607843 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (sl) config: sl split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 62.34700739744452 - type: f1 value: 59.957933424941636 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (sq) config: sq split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 61.23402824478815 - type: f1 value: 57.98836976018471 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (sv) config: sv split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 68.54068594485541 - type: f1 value: 65.43849680666855 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (sw) config: sw split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 55.998655010087425 - type: f1 value: 52.83737515406804 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (ta) config: ta split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 58.71217215870882 - type: f1 value: 55.051794977833026 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (te) config: te split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 59.724277067921996 - type: f1 value: 56.33485571838306 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (th) config: th split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 65.59515803631473 - type: f1 value: 64.96772366193588 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (tl) config: tl split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 60.860793544048406 - type: f1 value: 58.148845819115394 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (tr) config: tr split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 67.40753194351043 - type: f1 value: 63.18903778054698 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (ur) config: ur split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 61.52320107599194 - type: f1 value: 58.356144563398516 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (vi) config: vi split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 66.17014122394083 - type: f1 value: 63.919964062638925 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (zh-CN) config: zh-CN split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 69.15601882985878 - type: f1 value: 67.01451905761371 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (zh-TW) config: zh-TW split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 64.65030262273034 - type: f1 value: 64.14420425129063 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (af) config: af split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 65.08742434431743 - type: f1 value: 63.044060042311756 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (am) config: am split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 58.52387357094821 - type: f1 value: 56.82398588814534 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (ar) config: ar split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 62.239408204438476 - type: f1 value: 61.92570286170469 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (az) config: az split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 63.74915938130463 - type: f1 value: 62.130740689396276 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (bn) config: bn split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 65.00336247478144 - type: f1 value: 63.71080635228055 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (cy) config: cy split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 52.837928715534645 - type: f1 value: 50.390741680320836 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (da) config: da split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 72.42098184263618 - type: f1 value: 71.41355113538995 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (de) config: de split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 71.95359784801613 - type: f1 value: 71.42699340156742 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (el) config: el split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 70.18157363819772 - type: f1 value: 69.74836113037671 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (en) config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 77.08137188971082 - type: f1 value: 76.78000685068261 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (es) config: es split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 71.5030262273033 - type: f1 value: 71.71620130425673 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (fa) config: fa split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 70.24546065904505 - type: f1 value: 69.07638311730359 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (fi) config: fi split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 69.12911903160726 - type: f1 value: 68.32651736539815 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (fr) config: fr split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 71.89307330195025 - type: f1 value: 71.33986549860187 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (he) config: he split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 67.44451916610626 - type: f1 value: 66.90192664503866 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (hi) config: hi split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 69.16274377942166 - type: f1 value: 68.01090953775066 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (hu) config: hu split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 70.75319435104237 - type: f1 value: 70.18035309201403 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (hy) config: hy split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 63.14391392064559 - type: f1 value: 61.48286540778145 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (id) config: id split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 70.70275722932078 - type: f1 value: 70.26164779846495 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (is) config: is split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 60.93813046402153 - type: f1 value: 58.8852862116525 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (it) config: it split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 72.320107599193 - type: f1 value: 72.19836409602924 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (ja) config: ja split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 74.65366509751176 - type: f1 value: 74.55188288799579 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (jv) config: jv split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 59.694014794889036 - type: f1 value: 58.11353311721067 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (ka) config: ka split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 54.37457969065231 - type: f1 value: 52.81306134311697 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (km) config: km split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 48.3086751849361 - type: f1 value: 45.396449765419376 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (kn) config: kn split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 62.151983860121064 - type: f1 value: 60.31762544281696 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (ko) config: ko split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 72.44788164088769 - type: f1 value: 71.68150151736367 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (lv) config: lv split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 62.81439139206455 - type: f1 value: 62.06735559105593 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (ml) config: ml split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 68.04303967720242 - type: f1 value: 66.68298851670133 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (mn) config: mn split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 61.43913920645595 - type: f1 value: 60.25605977560783 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (ms) config: ms split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 66.90316072629456 - type: f1 value: 65.1325924692381 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (my) config: my split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 61.63752521856086 - type: f1 value: 59.14284778039585 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (nb) config: nb split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 71.63080026899797 - type: f1 value: 70.89771864626877 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (nl) config: nl split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 72.10827168796234 - type: f1 value: 71.71954219691159 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (pl) config: pl split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 70.59515803631471 - type: f1 value: 70.05040128099003 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (pt) config: pt split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 70.83389374579691 - type: f1 value: 70.84877936562735 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (ro) config: ro split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 69.18628110289173 - type: f1 value: 68.97232927921841 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (ru) config: ru split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 72.99260255548083 - type: f1 value: 72.85139492157732 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (sl) config: sl split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 65.26227303295225 - type: f1 value: 65.08833655469431 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (sq) config: sq split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 66.48621385339611 - type: f1 value: 64.43483199071298 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (sv) config: sv split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 73.14391392064559 - type: f1 value: 72.2580822579741 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (sw) config: sw split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 59.88567585743107 - type: f1 value: 58.3073765932569 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (ta) config: ta split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 62.38399462004034 - type: f1 value: 60.82139544252606 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (te) config: te split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 62.58574310692671 - type: f1 value: 60.71443370385374 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (th) config: th split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 71.61398789509079 - type: f1 value: 70.99761812049401 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (tl) config: tl split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 62.73705447209146 - type: f1 value: 61.680849331794796 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (tr) config: tr split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 71.66778749159381 - type: f1 value: 71.17320646080115 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (ur) config: ur split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 64.640215198386 - type: f1 value: 63.301805157015444 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (vi) config: vi split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 70.00672494956288 - type: f1 value: 70.26005548582106 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (zh-CN) config: zh-CN split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 75.42030934767989 - type: f1 value: 75.2074842882598 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (zh-TW) config: zh-TW split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 70.69266980497646 - type: f1 value: 70.94103167391192 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-p2p name: MTEB MedrxivClusteringP2P config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 28.91697191169135 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-s2s name: MTEB MedrxivClusteringS2S config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 28.434000079573313 - task: type: Reranking dataset: type: mteb/mind_small name: MTEB MindSmallReranking config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 30.96683513343383 - type: mrr value: 31.967364078714834 - task: type: Retrieval dataset: type: nfcorpus name: MTEB NFCorpus config: default split: test revision: None metrics: - type: map_at_1 value: 5.5280000000000005 - type: map_at_10 value: 11.793 - type: map_at_100 value: 14.496999999999998 - type: map_at_1000 value: 15.783 - type: map_at_3 value: 8.838 - type: map_at_5 value: 10.07 - type: mrr_at_1 value: 43.653 - type: mrr_at_10 value: 51.531000000000006 - type: mrr_at_100 value: 52.205 - type: mrr_at_1000 value: 52.242999999999995 - type: mrr_at_3 value: 49.431999999999995 - type: mrr_at_5 value: 50.470000000000006 - type: ndcg_at_1 value: 42.415000000000006 - type: ndcg_at_10 value: 32.464999999999996 - type: ndcg_at_100 value: 28.927999999999997 - type: ndcg_at_1000 value: 37.629000000000005 - type: ndcg_at_3 value: 37.845 - type: ndcg_at_5 value: 35.147 - type: precision_at_1 value: 43.653 - type: precision_at_10 value: 23.932000000000002 - type: precision_at_100 value: 7.17 - type: precision_at_1000 value: 1.967 - type: precision_at_3 value: 35.397 - type: precision_at_5 value: 29.907 - type: recall_at_1 value: 5.5280000000000005 - type: recall_at_10 value: 15.568000000000001 - type: recall_at_100 value: 28.54 - type: recall_at_1000 value: 59.864 - type: recall_at_3 value: 9.822000000000001 - type: recall_at_5 value: 11.726 - task: type: Retrieval dataset: type: nq name: MTEB NQ config: default split: test revision: None metrics: - type: map_at_1 value: 37.041000000000004 - type: map_at_10 value: 52.664 - type: map_at_100 value: 53.477 - type: map_at_1000 value: 53.505 - type: map_at_3 value: 48.510999999999996 - type: map_at_5 value: 51.036 - type: mrr_at_1 value: 41.338 - type: mrr_at_10 value: 55.071000000000005 - type: mrr_at_100 value: 55.672 - type: mrr_at_1000 value: 55.689 - type: mrr_at_3 value: 51.82 - type: mrr_at_5 value: 53.852 - type: ndcg_at_1 value: 41.338 - type: ndcg_at_10 value: 60.01800000000001 - type: ndcg_at_100 value: 63.409000000000006 - type: ndcg_at_1000 value: 64.017 - type: ndcg_at_3 value: 52.44799999999999 - type: ndcg_at_5 value: 56.571000000000005 - type: precision_at_1 value: 41.338 - type: precision_at_10 value: 9.531 - type: precision_at_100 value: 1.145 - type: precision_at_1000 value: 0.12 - type: precision_at_3 value: 23.416 - type: precision_at_5 value: 16.46 - type: recall_at_1 value: 37.041000000000004 - type: recall_at_10 value: 79.76299999999999 - type: recall_at_100 value: 94.39 - type: recall_at_1000 value: 98.851 - type: recall_at_3 value: 60.465 - type: recall_at_5 value: 69.906 - task: type: Retrieval dataset: type: quora name: MTEB QuoraRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 69.952 - type: map_at_10 value: 83.758 - type: map_at_100 value: 84.406 - type: map_at_1000 value: 84.425 - type: map_at_3 value: 80.839 - type: map_at_5 value: 82.646 - type: mrr_at_1 value: 80.62 - type: mrr_at_10 value: 86.947 - type: mrr_at_100 value: 87.063 - type: mrr_at_1000 value: 87.064 - type: mrr_at_3 value: 85.96000000000001 - type: mrr_at_5 value: 86.619 - type: ndcg_at_1 value: 80.63 - type: ndcg_at_10 value: 87.64800000000001 - type: ndcg_at_100 value: 88.929 - type: ndcg_at_1000 value: 89.054 - type: ndcg_at_3 value: 84.765 - type: ndcg_at_5 value: 86.291 - type: precision_at_1 value: 80.63 - type: precision_at_10 value: 13.314 - type: precision_at_100 value: 1.525 - type: precision_at_1000 value: 0.157 - type: precision_at_3 value: 37.1 - type: precision_at_5 value: 24.372 - type: recall_at_1 value: 69.952 - type: recall_at_10 value: 94.955 - type: recall_at_100 value: 99.38 - type: recall_at_1000 value: 99.96000000000001 - type: recall_at_3 value: 86.60600000000001 - type: recall_at_5 value: 90.997 - task: type: Clustering dataset: type: mteb/reddit-clustering name: MTEB RedditClustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 42.41329517878427 - task: type: Clustering dataset: type: mteb/reddit-clustering-p2p name: MTEB RedditClusteringP2P config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 55.171278362748666 - task: type: Retrieval dataset: type: scidocs name: MTEB SCIDOCS config: default split: test revision: None metrics: - type: map_at_1 value: 4.213 - type: map_at_10 value: 9.895 - type: map_at_100 value: 11.776 - type: map_at_1000 value: 12.084 - type: map_at_3 value: 7.2669999999999995 - type: map_at_5 value: 8.620999999999999 - type: mrr_at_1 value: 20.8 - type: mrr_at_10 value: 31.112000000000002 - type: mrr_at_100 value: 32.274 - type: mrr_at_1000 value: 32.35 - type: mrr_at_3 value: 28.133000000000003 - type: mrr_at_5 value: 29.892999999999997 - type: ndcg_at_1 value: 20.8 - type: ndcg_at_10 value: 17.163999999999998 - type: ndcg_at_100 value: 24.738 - type: ndcg_at_1000 value: 30.316 - type: ndcg_at_3 value: 16.665 - type: ndcg_at_5 value: 14.478 - type: precision_at_1 value: 20.8 - type: precision_at_10 value: 8.74 - type: precision_at_100 value: 1.963 - type: precision_at_1000 value: 0.33 - type: precision_at_3 value: 15.467 - type: precision_at_5 value: 12.6 - type: recall_at_1 value: 4.213 - type: recall_at_10 value: 17.698 - type: recall_at_100 value: 39.838 - type: recall_at_1000 value: 66.893 - type: recall_at_3 value: 9.418 - type: recall_at_5 value: 12.773000000000001 - task: type: STS dataset: type: mteb/sickr-sts name: MTEB SICK-R config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 82.90453315738294 - type: cos_sim_spearman value: 78.51197850080254 - type: euclidean_pearson value: 80.09647123597748 - type: euclidean_spearman value: 78.63548011514061 - type: manhattan_pearson value: 80.10645285675231 - type: manhattan_spearman value: 78.57861806068901 - task: type: STS dataset: type: mteb/sts12-sts name: MTEB STS12 config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 84.2616156846401 - type: cos_sim_spearman value: 76.69713867850156 - type: euclidean_pearson value: 77.97948563800394 - type: euclidean_spearman value: 74.2371211567807 - type: manhattan_pearson value: 77.69697879669705 - type: manhattan_spearman value: 73.86529778022278 - task: type: STS dataset: type: mteb/sts13-sts name: MTEB STS13 config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 77.0293269315045 - type: cos_sim_spearman value: 78.02555120584198 - type: euclidean_pearson value: 78.25398100379078 - type: euclidean_spearman value: 78.66963870599464 - type: manhattan_pearson value: 78.14314682167348 - type: manhattan_spearman value: 78.57692322969135 - task: type: STS dataset: type: mteb/sts14-sts name: MTEB STS14 config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 79.16989925136942 - type: cos_sim_spearman value: 76.5996225327091 - type: euclidean_pearson value: 77.8319003279786 - type: euclidean_spearman value: 76.42824009468998 - type: manhattan_pearson value: 77.69118862737736 - type: manhattan_spearman value: 76.25568104762812 - task: type: STS dataset: type: mteb/sts15-sts name: MTEB STS15 config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 87.42012286935325 - type: cos_sim_spearman value: 88.15654297884122 - type: euclidean_pearson value: 87.34082819427852 - type: euclidean_spearman value: 88.06333589547084 - type: manhattan_pearson value: 87.25115596784842 - type: manhattan_spearman value: 87.9559927695203 - task: type: STS dataset: type: mteb/sts16-sts name: MTEB STS16 config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 82.88222044996712 - type: cos_sim_spearman value: 84.28476589061077 - type: euclidean_pearson value: 83.17399758058309 - type: euclidean_spearman value: 83.85497357244542 - type: manhattan_pearson value: 83.0308397703786 - type: manhattan_spearman value: 83.71554539935046 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (ko-ko) config: ko-ko split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 80.20682986257339 - type: cos_sim_spearman value: 79.94567120362092 - type: euclidean_pearson value: 79.43122480368902 - type: euclidean_spearman value: 79.94802077264987 - type: manhattan_pearson value: 79.32653021527081 - type: manhattan_spearman value: 79.80961146709178 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (ar-ar) config: ar-ar split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 74.46578144394383 - type: cos_sim_spearman value: 74.52496637472179 - type: euclidean_pearson value: 72.2903807076809 - type: euclidean_spearman value: 73.55549359771645 - type: manhattan_pearson value: 72.09324837709393 - type: manhattan_spearman value: 73.36743103606581 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-ar) config: en-ar split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 71.37272335116 - type: cos_sim_spearman value: 71.26702117766037 - type: euclidean_pearson value: 67.114829954434 - type: euclidean_spearman value: 66.37938893947761 - type: manhattan_pearson value: 66.79688574095246 - type: manhattan_spearman value: 66.17292828079667 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-de) config: en-de split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 80.61016770129092 - type: cos_sim_spearman value: 82.08515426632214 - type: euclidean_pearson value: 80.557340361131 - type: euclidean_spearman value: 80.37585812266175 - type: manhattan_pearson value: 80.6782873404285 - type: manhattan_spearman value: 80.6678073032024 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-en) config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 87.00150745350108 - type: cos_sim_spearman value: 87.83441972211425 - type: euclidean_pearson value: 87.94826702308792 - type: euclidean_spearman value: 87.46143974860725 - type: manhattan_pearson value: 87.97560344306105 - type: manhattan_spearman value: 87.5267102829796 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-tr) config: en-tr split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 64.76325252267235 - type: cos_sim_spearman value: 63.32615095463905 - type: euclidean_pearson value: 64.07920669155716 - type: euclidean_spearman value: 61.21409893072176 - type: manhattan_pearson value: 64.26308625680016 - type: manhattan_spearman value: 61.2438185254079 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (es-en) config: es-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 75.82644463022595 - type: cos_sim_spearman value: 76.50381269945073 - type: euclidean_pearson value: 75.1328548315934 - type: euclidean_spearman value: 75.63761139408453 - type: manhattan_pearson value: 75.18610101241407 - type: manhattan_spearman value: 75.30669266354164 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (es-es) config: es-es split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 87.49994164686832 - type: cos_sim_spearman value: 86.73743986245549 - type: euclidean_pearson value: 86.8272894387145 - type: euclidean_spearman value: 85.97608491000507 - type: manhattan_pearson value: 86.74960140396779 - type: manhattan_spearman value: 85.79285984190273 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (fr-en) config: fr-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 79.58172210788469 - type: cos_sim_spearman value: 80.17516468334607 - type: euclidean_pearson value: 77.56537843470504 - type: euclidean_spearman value: 77.57264627395521 - type: manhattan_pearson value: 78.09703521695943 - type: manhattan_spearman value: 78.15942760916954 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (it-en) config: it-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 79.7589932931751 - type: cos_sim_spearman value: 80.15210089028162 - type: euclidean_pearson value: 77.54135223516057 - type: euclidean_spearman value: 77.52697996368764 - type: manhattan_pearson value: 77.65734439572518 - type: manhattan_spearman value: 77.77702992016121 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (nl-en) config: nl-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 79.16682365511267 - type: cos_sim_spearman value: 79.25311267628506 - type: euclidean_pearson value: 77.54882036762244 - type: euclidean_spearman value: 77.33212935194827 - type: manhattan_pearson value: 77.98405516064015 - type: manhattan_spearman value: 77.85075717865719 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (en) config: en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 59.10473294775917 - type: cos_sim_spearman value: 61.82780474476838 - type: euclidean_pearson value: 45.885111672377256 - type: euclidean_spearman value: 56.88306351932454 - type: manhattan_pearson value: 46.101218127323186 - type: manhattan_spearman value: 56.80953694186333 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (de) config: de split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 45.781923079584146 - type: cos_sim_spearman value: 55.95098449691107 - type: euclidean_pearson value: 25.4571031323205 - type: euclidean_spearman value: 49.859978118078935 - type: manhattan_pearson value: 25.624938455041384 - type: manhattan_spearman value: 49.99546185049401 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (es) config: es split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 60.00618133997907 - type: cos_sim_spearman value: 66.57896677718321 - type: euclidean_pearson value: 42.60118466388821 - type: euclidean_spearman value: 62.8210759715209 - type: manhattan_pearson value: 42.63446860604094 - type: manhattan_spearman value: 62.73803068925271 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (pl) config: pl split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 28.460759121626943 - type: cos_sim_spearman value: 34.13459007469131 - type: euclidean_pearson value: 6.0917739325525195 - type: euclidean_spearman value: 27.9947262664867 - type: manhattan_pearson value: 6.16877864169911 - type: manhattan_spearman value: 28.00664163971514 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (tr) config: tr split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 57.42546621771696 - type: cos_sim_spearman value: 63.699663168970474 - type: euclidean_pearson value: 38.12085278789738 - type: euclidean_spearman value: 58.12329140741536 - type: manhattan_pearson value: 37.97364549443335 - type: manhattan_spearman value: 57.81545502318733 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (ar) config: ar split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 46.82241380954213 - type: cos_sim_spearman value: 57.86569456006391 - type: euclidean_pearson value: 31.80480070178813 - type: euclidean_spearman value: 52.484000620130104 - type: manhattan_pearson value: 31.952708554646097 - type: manhattan_spearman value: 52.8560972356195 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (ru) config: ru split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 52.00447170498087 - type: cos_sim_spearman value: 60.664116225735164 - type: euclidean_pearson value: 33.87382555421702 - type: euclidean_spearman value: 55.74649067458667 - type: manhattan_pearson value: 33.99117246759437 - type: manhattan_spearman value: 55.98749034923899 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (zh) config: zh split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 58.06497233105448 - type: cos_sim_spearman value: 65.62968801135676 - type: euclidean_pearson value: 47.482076613243905 - type: euclidean_spearman value: 62.65137791498299 - type: manhattan_pearson value: 47.57052626104093 - type: manhattan_spearman value: 62.436916516613294 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (fr) config: fr split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 70.49397298562575 - type: cos_sim_spearman value: 74.79604041187868 - type: euclidean_pearson value: 49.661891561317795 - type: euclidean_spearman value: 70.31535537621006 - type: manhattan_pearson value: 49.553715741850006 - type: manhattan_spearman value: 70.24779344636806 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (de-en) config: de-en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 55.640574515348696 - type: cos_sim_spearman value: 54.927959317689 - type: euclidean_pearson value: 29.00139666967476 - type: euclidean_spearman value: 41.86386566971605 - type: manhattan_pearson value: 29.47411067730344 - type: manhattan_spearman value: 42.337438424952786 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (es-en) config: es-en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 68.14095292259312 - type: cos_sim_spearman value: 73.99017581234789 - type: euclidean_pearson value: 46.46304297872084 - type: euclidean_spearman value: 60.91834114800041 - type: manhattan_pearson value: 47.07072666338692 - type: manhattan_spearman value: 61.70415727977926 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (it) config: it split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 73.27184653359575 - type: cos_sim_spearman value: 77.76070252418626 - type: euclidean_pearson value: 62.30586577544778 - type: euclidean_spearman value: 75.14246629110978 - type: manhattan_pearson value: 62.328196884927046 - type: manhattan_spearman value: 75.1282792981433 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (pl-en) config: pl-en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 71.59448528829957 - type: cos_sim_spearman value: 70.37277734222123 - type: euclidean_pearson value: 57.63145565721123 - type: euclidean_spearman value: 66.10113048304427 - type: manhattan_pearson value: 57.18897811586808 - type: manhattan_spearman value: 66.5595511215901 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (zh-en) config: zh-en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 66.37520607720838 - type: cos_sim_spearman value: 69.92282148997948 - type: euclidean_pearson value: 40.55768770125291 - type: euclidean_spearman value: 55.189128944669605 - type: manhattan_pearson value: 41.03566433468883 - type: manhattan_spearman value: 55.61251893174558 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (es-it) config: es-it split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 57.791929533771835 - type: cos_sim_spearman value: 66.45819707662093 - type: euclidean_pearson value: 39.03686018511092 - type: euclidean_spearman value: 56.01282695640428 - type: manhattan_pearson value: 38.91586623619632 - type: manhattan_spearman value: 56.69394943612747 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (de-fr) config: de-fr split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 47.82224468473866 - type: cos_sim_spearman value: 59.467307194781164 - type: euclidean_pearson value: 27.428459190256145 - type: euclidean_spearman value: 60.83463107397519 - type: manhattan_pearson value: 27.487391578496638 - type: manhattan_spearman value: 61.281380460246496 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (de-pl) config: de-pl split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 16.306666792752644 - type: cos_sim_spearman value: 39.35486427252405 - type: euclidean_pearson value: -2.7887154897955435 - type: euclidean_spearman value: 27.1296051831719 - type: manhattan_pearson value: -3.202291270581297 - type: manhattan_spearman value: 26.32895849218158 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (fr-pl) config: fr-pl split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 59.67006803805076 - type: cos_sim_spearman value: 73.24670207647144 - type: euclidean_pearson value: 46.91884681500483 - type: euclidean_spearman value: 16.903085094570333 - type: manhattan_pearson value: 46.88391675325812 - type: manhattan_spearman value: 28.17180849095055 - task: type: STS dataset: type: mteb/stsbenchmark-sts name: MTEB STSBenchmark config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 83.79555591223837 - type: cos_sim_spearman value: 85.63658602085185 - type: euclidean_pearson value: 85.22080894037671 - type: euclidean_spearman value: 85.54113580167038 - type: manhattan_pearson value: 85.1639505960118 - type: manhattan_spearman value: 85.43502665436196 - task: type: Reranking dataset: type: mteb/scidocs-reranking name: MTEB SciDocsRR config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 80.73900991689766 - type: mrr value: 94.81624131133934 - task: type: Retrieval dataset: type: scifact name: MTEB SciFact config: default split: test revision: None metrics: - type: map_at_1 value: 55.678000000000004 - type: map_at_10 value: 65.135 - type: map_at_100 value: 65.824 - type: map_at_1000 value: 65.852 - type: map_at_3 value: 62.736000000000004 - type: map_at_5 value: 64.411 - type: mrr_at_1 value: 58.333 - type: mrr_at_10 value: 66.5 - type: mrr_at_100 value: 67.053 - type: mrr_at_1000 value: 67.08 - type: mrr_at_3 value: 64.944 - type: mrr_at_5 value: 65.89399999999999 - type: ndcg_at_1 value: 58.333 - type: ndcg_at_10 value: 69.34700000000001 - type: ndcg_at_100 value: 72.32 - type: ndcg_at_1000 value: 73.014 - type: ndcg_at_3 value: 65.578 - type: ndcg_at_5 value: 67.738 - type: precision_at_1 value: 58.333 - type: precision_at_10 value: 9.033 - type: precision_at_100 value: 1.0670000000000002 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 25.444 - type: precision_at_5 value: 16.933 - type: recall_at_1 value: 55.678000000000004 - type: recall_at_10 value: 80.72200000000001 - type: recall_at_100 value: 93.93299999999999 - type: recall_at_1000 value: 99.333 - type: recall_at_3 value: 70.783 - type: recall_at_5 value: 75.978 - task: type: PairClassification dataset: type: mteb/sprintduplicatequestions-pairclassification name: MTEB SprintDuplicateQuestions config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.74653465346535 - type: cos_sim_ap value: 93.01476369929063 - type: cos_sim_f1 value: 86.93009118541033 - type: cos_sim_precision value: 88.09034907597535 - type: cos_sim_recall value: 85.8 - type: dot_accuracy value: 99.22970297029703 - type: dot_ap value: 51.58725659485144 - type: dot_f1 value: 53.51351351351352 - type: dot_precision value: 58.235294117647065 - type: dot_recall value: 49.5 - type: euclidean_accuracy value: 99.74356435643564 - type: euclidean_ap value: 92.40332894384368 - type: euclidean_f1 value: 86.97838109602817 - type: euclidean_precision value: 87.46208291203236 - type: euclidean_recall value: 86.5 - type: manhattan_accuracy value: 99.73069306930694 - type: manhattan_ap value: 92.01320815721121 - type: manhattan_f1 value: 86.4135864135864 - type: manhattan_precision value: 86.32734530938124 - type: manhattan_recall value: 86.5 - type: max_accuracy value: 99.74653465346535 - type: max_ap value: 93.01476369929063 - type: max_f1 value: 86.97838109602817 - task: type: Clustering dataset: type: mteb/stackexchange-clustering name: MTEB StackExchangeClustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 55.2660514302523 - task: type: Clustering dataset: type: mteb/stackexchange-clustering-p2p name: MTEB StackExchangeClusteringP2P config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 30.4637783572547 - task: type: Reranking dataset: type: mteb/stackoverflowdupquestions-reranking name: MTEB StackOverflowDupQuestions config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 49.41377758357637 - type: mrr value: 50.138451213818854 - task: type: Summarization dataset: type: mteb/summeval name: MTEB SummEval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 28.887846011166594 - type: cos_sim_spearman value: 30.10823258355903 - type: dot_pearson value: 12.888049550236385 - type: dot_spearman value: 12.827495903098123 - task: type: Retrieval dataset: type: trec-covid name: MTEB TRECCOVID config: default split: test revision: None metrics: - type: map_at_1 value: 0.21 - type: map_at_10 value: 1.667 - type: map_at_100 value: 9.15 - type: map_at_1000 value: 22.927 - type: map_at_3 value: 0.573 - type: map_at_5 value: 0.915 - type: mrr_at_1 value: 80 - type: mrr_at_10 value: 87.167 - type: mrr_at_100 value: 87.167 - type: mrr_at_1000 value: 87.167 - type: mrr_at_3 value: 85.667 - type: mrr_at_5 value: 87.167 - type: ndcg_at_1 value: 76 - type: ndcg_at_10 value: 69.757 - type: ndcg_at_100 value: 52.402 - type: ndcg_at_1000 value: 47.737 - type: ndcg_at_3 value: 71.866 - type: ndcg_at_5 value: 72.225 - type: precision_at_1 value: 80 - type: precision_at_10 value: 75 - type: precision_at_100 value: 53.959999999999994 - type: precision_at_1000 value: 21.568 - type: precision_at_3 value: 76.667 - type: precision_at_5 value: 78 - type: recall_at_1 value: 0.21 - type: recall_at_10 value: 1.9189999999999998 - type: recall_at_100 value: 12.589 - type: recall_at_1000 value: 45.312000000000005 - type: recall_at_3 value: 0.61 - type: recall_at_5 value: 1.019 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (sqi-eng) config: sqi-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 92.10000000000001 - type: f1 value: 90.06 - type: precision value: 89.17333333333333 - type: recall value: 92.10000000000001 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (fry-eng) config: fry-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 56.06936416184971 - type: f1 value: 50.87508028259473 - type: precision value: 48.97398843930635 - type: recall value: 56.06936416184971 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (kur-eng) config: kur-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 57.3170731707317 - type: f1 value: 52.96080139372822 - type: precision value: 51.67861124382864 - type: recall value: 57.3170731707317 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (tur-eng) config: tur-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 94.3 - type: f1 value: 92.67333333333333 - type: precision value: 91.90833333333333 - type: recall value: 94.3 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (deu-eng) config: deu-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 97.7 - type: f1 value: 97.07333333333332 - type: precision value: 96.79500000000002 - type: recall value: 97.7 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (nld-eng) config: nld-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 94.69999999999999 - type: f1 value: 93.2 - type: precision value: 92.48333333333333 - type: recall value: 94.69999999999999 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ron-eng) config: ron-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 92.9 - type: f1 value: 91.26666666666667 - type: precision value: 90.59444444444445 - type: recall value: 92.9 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ang-eng) config: ang-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 34.32835820895522 - type: f1 value: 29.074180380150533 - type: precision value: 28.068207322920596 - type: recall value: 34.32835820895522 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ido-eng) config: ido-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 78.5 - type: f1 value: 74.3945115995116 - type: precision value: 72.82967843459222 - type: recall value: 78.5 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (jav-eng) config: jav-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 66.34146341463415 - type: f1 value: 61.2469400518181 - type: precision value: 59.63977756660683 - type: recall value: 66.34146341463415 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (isl-eng) config: isl-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 80.9 - type: f1 value: 76.90349206349207 - type: precision value: 75.32921568627451 - type: recall value: 80.9 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (slv-eng) config: slv-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 84.93317132442284 - type: f1 value: 81.92519105034295 - type: precision value: 80.71283920615635 - type: recall value: 84.93317132442284 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (cym-eng) config: cym-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 71.1304347826087 - type: f1 value: 65.22394755003451 - type: precision value: 62.912422360248435 - type: recall value: 71.1304347826087 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (kaz-eng) config: kaz-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 79.82608695652173 - type: f1 value: 75.55693581780538 - type: precision value: 73.79420289855072 - type: recall value: 79.82608695652173 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (est-eng) config: est-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 74 - type: f1 value: 70.51022222222223 - type: precision value: 69.29673599347512 - type: recall value: 74 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (heb-eng) config: heb-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 78.7 - type: f1 value: 74.14238095238095 - type: precision value: 72.27214285714285 - type: recall value: 78.7 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (gla-eng) config: gla-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 48.97466827503016 - type: f1 value: 43.080330405420874 - type: precision value: 41.36505499593557 - type: recall value: 48.97466827503016 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (mar-eng) config: mar-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 89.60000000000001 - type: f1 value: 86.62333333333333 - type: precision value: 85.225 - type: recall value: 89.60000000000001 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (lat-eng) config: lat-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 45.2 - type: f1 value: 39.5761253006253 - type: precision value: 37.991358436312 - type: recall value: 45.2 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (bel-eng) config: bel-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 89.5 - type: f1 value: 86.70333333333333 - type: precision value: 85.53166666666667 - type: recall value: 89.5 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (pms-eng) config: pms-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 50.095238095238095 - type: f1 value: 44.60650460650461 - type: precision value: 42.774116796477045 - type: recall value: 50.095238095238095 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (gle-eng) config: gle-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 63.4 - type: f1 value: 58.35967261904762 - type: precision value: 56.54857142857143 - type: recall value: 63.4 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (pes-eng) config: pes-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 89.2 - type: f1 value: 87.075 - type: precision value: 86.12095238095239 - type: recall value: 89.2 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (nob-eng) config: nob-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 96.8 - type: f1 value: 95.90333333333334 - type: precision value: 95.50833333333333 - type: recall value: 96.8 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (bul-eng) config: bul-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 90.9 - type: f1 value: 88.6288888888889 - type: precision value: 87.61607142857142 - type: recall value: 90.9 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (cbk-eng) config: cbk-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 65.2 - type: f1 value: 60.54377630539395 - type: precision value: 58.89434482711381 - type: recall value: 65.2 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (hun-eng) config: hun-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 87 - type: f1 value: 84.32412698412699 - type: precision value: 83.25527777777778 - type: recall value: 87 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (uig-eng) config: uig-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 68.7 - type: f1 value: 63.07883541295306 - type: precision value: 61.06117424242426 - type: recall value: 68.7 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (rus-eng) config: rus-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 93.7 - type: f1 value: 91.78333333333335 - type: precision value: 90.86666666666667 - type: recall value: 93.7 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (spa-eng) config: spa-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 97.7 - type: f1 value: 96.96666666666667 - type: precision value: 96.61666666666667 - type: recall value: 97.7 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (hye-eng) config: hye-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 88.27493261455525 - type: f1 value: 85.90745732255168 - type: precision value: 84.91389637616052 - type: recall value: 88.27493261455525 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (tel-eng) config: tel-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 90.5982905982906 - type: f1 value: 88.4900284900285 - type: precision value: 87.57122507122507 - type: recall value: 90.5982905982906 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (afr-eng) config: afr-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 89.5 - type: f1 value: 86.90769841269842 - type: precision value: 85.80178571428571 - type: recall value: 89.5 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (mon-eng) config: mon-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 82.5 - type: f1 value: 78.36796536796538 - type: precision value: 76.82196969696969 - type: recall value: 82.5 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (arz-eng) config: arz-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 71.48846960167715 - type: f1 value: 66.78771089148448 - type: precision value: 64.98302885095339 - type: recall value: 71.48846960167715 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (hrv-eng) config: hrv-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 94.1 - type: f1 value: 92.50333333333333 - type: precision value: 91.77499999999999 - type: recall value: 94.1 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (nov-eng) config: nov-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 71.20622568093385 - type: f1 value: 66.83278891450098 - type: precision value: 65.35065777283677 - type: recall value: 71.20622568093385 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (gsw-eng) config: gsw-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 48.717948717948715 - type: f1 value: 43.53146853146853 - type: precision value: 42.04721204721204 - type: recall value: 48.717948717948715 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (nds-eng) config: nds-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 58.5 - type: f1 value: 53.8564991863928 - type: precision value: 52.40329436122275 - type: recall value: 58.5 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ukr-eng) config: ukr-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 90.8 - type: f1 value: 88.29 - type: precision value: 87.09166666666667 - type: recall value: 90.8 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (uzb-eng) config: uzb-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 67.28971962616822 - type: f1 value: 62.63425307817832 - type: precision value: 60.98065939771546 - type: recall value: 67.28971962616822 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (lit-eng) config: lit-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 78.7 - type: f1 value: 75.5264472455649 - type: precision value: 74.38205086580086 - type: recall value: 78.7 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ina-eng) config: ina-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 88.7 - type: f1 value: 86.10809523809525 - type: precision value: 85.07602564102565 - type: recall value: 88.7 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (lfn-eng) config: lfn-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 56.99999999999999 - type: f1 value: 52.85487521402737 - type: precision value: 51.53985162713104 - type: recall value: 56.99999999999999 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (zsm-eng) config: zsm-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 94 - type: f1 value: 92.45333333333333 - type: precision value: 91.79166666666667 - type: recall value: 94 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ita-eng) config: ita-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 92.30000000000001 - type: f1 value: 90.61333333333333 - type: precision value: 89.83333333333331 - type: recall value: 92.30000000000001 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (cmn-eng) config: cmn-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 94.69999999999999 - type: f1 value: 93.34555555555555 - type: precision value: 92.75416666666668 - type: recall value: 94.69999999999999 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (lvs-eng) config: lvs-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 80.2 - type: f1 value: 76.6563035113035 - type: precision value: 75.3014652014652 - type: recall value: 80.2 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (glg-eng) config: glg-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 84.7 - type: f1 value: 82.78689263765207 - type: precision value: 82.06705086580087 - type: recall value: 84.7 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ceb-eng) config: ceb-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 50.33333333333333 - type: f1 value: 45.461523661523664 - type: precision value: 43.93545574795575 - type: recall value: 50.33333333333333 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (bre-eng) config: bre-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 6.6000000000000005 - type: f1 value: 5.442121400446441 - type: precision value: 5.146630385487529 - type: recall value: 6.6000000000000005 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ben-eng) config: ben-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 85 - type: f1 value: 81.04666666666667 - type: precision value: 79.25 - type: recall value: 85 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (swg-eng) config: swg-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 47.32142857142857 - type: f1 value: 42.333333333333336 - type: precision value: 40.69196428571429 - type: recall value: 47.32142857142857 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (arq-eng) config: arq-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 30.735455543358945 - type: f1 value: 26.73616790022338 - type: precision value: 25.397823220451283 - type: recall value: 30.735455543358945 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (kab-eng) config: kab-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 25.1 - type: f1 value: 21.975989896371022 - type: precision value: 21.059885632257203 - type: recall value: 25.1 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (fra-eng) config: fra-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 94.3 - type: f1 value: 92.75666666666666 - type: precision value: 92.06166666666665 - type: recall value: 94.3 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (por-eng) config: por-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 94.1 - type: f1 value: 92.74 - type: precision value: 92.09166666666667 - type: recall value: 94.1 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (tat-eng) config: tat-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 71.3 - type: f1 value: 66.922442002442 - type: precision value: 65.38249567099568 - type: recall value: 71.3 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (oci-eng) config: oci-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 40.300000000000004 - type: f1 value: 35.78682789299971 - type: precision value: 34.66425128716588 - type: recall value: 40.300000000000004 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (pol-eng) config: pol-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 96 - type: f1 value: 94.82333333333334 - type: precision value: 94.27833333333334 - type: recall value: 96 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (war-eng) config: war-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 51.1 - type: f1 value: 47.179074753133584 - type: precision value: 46.06461044702424 - type: recall value: 51.1 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (aze-eng) config: aze-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 87.7 - type: f1 value: 84.71 - type: precision value: 83.46166666666667 - type: recall value: 87.7 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (vie-eng) config: vie-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 95.8 - type: f1 value: 94.68333333333334 - type: precision value: 94.13333333333334 - type: recall value: 95.8 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (nno-eng) config: nno-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 85.39999999999999 - type: f1 value: 82.5577380952381 - type: precision value: 81.36833333333334 - type: recall value: 85.39999999999999 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (cha-eng) config: cha-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 21.16788321167883 - type: f1 value: 16.948865627297987 - type: precision value: 15.971932568647897 - type: recall value: 21.16788321167883 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (mhr-eng) config: mhr-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 6.9 - type: f1 value: 5.515526831658907 - type: precision value: 5.141966366966367 - type: recall value: 6.9 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (dan-eng) config: dan-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 93.2 - type: f1 value: 91.39666666666668 - type: precision value: 90.58666666666667 - type: recall value: 93.2 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ell-eng) config: ell-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 92.2 - type: f1 value: 89.95666666666666 - type: precision value: 88.92833333333333 - type: recall value: 92.2 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (amh-eng) config: amh-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 79.76190476190477 - type: f1 value: 74.93386243386244 - type: precision value: 73.11011904761904 - type: recall value: 79.76190476190477 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (pam-eng) config: pam-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 8.799999999999999 - type: f1 value: 6.921439712248537 - type: precision value: 6.489885109680683 - type: recall value: 8.799999999999999 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (hsb-eng) config: hsb-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 45.75569358178054 - type: f1 value: 40.34699501312631 - type: precision value: 38.57886764719063 - type: recall value: 45.75569358178054 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (srp-eng) config: srp-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 91.4 - type: f1 value: 89.08333333333333 - type: precision value: 88.01666666666668 - type: recall value: 91.4 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (epo-eng) config: epo-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 93.60000000000001 - type: f1 value: 92.06690476190477 - type: precision value: 91.45095238095239 - type: recall value: 93.60000000000001 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (kzj-eng) config: kzj-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 7.5 - type: f1 value: 6.200363129378736 - type: precision value: 5.89115314822466 - type: recall value: 7.5 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (awa-eng) config: awa-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 73.59307359307358 - type: f1 value: 68.38933553219267 - type: precision value: 66.62698412698413 - type: recall value: 73.59307359307358 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (fao-eng) config: fao-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 69.8473282442748 - type: f1 value: 64.72373682297346 - type: precision value: 62.82834214131924 - type: recall value: 69.8473282442748 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (mal-eng) config: mal-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 97.5254730713246 - type: f1 value: 96.72489082969432 - type: precision value: 96.33672974284326 - type: recall value: 97.5254730713246 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ile-eng) config: ile-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 75.6 - type: f1 value: 72.42746031746033 - type: precision value: 71.14036630036631 - type: recall value: 75.6 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (bos-eng) config: bos-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 91.24293785310734 - type: f1 value: 88.86064030131826 - type: precision value: 87.73540489642184 - type: recall value: 91.24293785310734 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (cor-eng) config: cor-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 6.2 - type: f1 value: 4.383083659794954 - type: precision value: 4.027861324289673 - type: recall value: 6.2 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (cat-eng) config: cat-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 86.8 - type: f1 value: 84.09428571428572 - type: precision value: 83.00333333333333 - type: recall value: 86.8 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (eus-eng) config: eus-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 60.699999999999996 - type: f1 value: 56.1584972394755 - type: precision value: 54.713456330903135 - type: recall value: 60.699999999999996 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (yue-eng) config: yue-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 84.2 - type: f1 value: 80.66190476190475 - type: precision value: 79.19690476190476 - type: recall value: 84.2 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (swe-eng) config: swe-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 93.2 - type: f1 value: 91.33 - type: precision value: 90.45 - type: recall value: 93.2 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (dtp-eng) config: dtp-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 6.3 - type: f1 value: 5.126828976748276 - type: precision value: 4.853614328966668 - type: recall value: 6.3 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (kat-eng) config: kat-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 81.76943699731903 - type: f1 value: 77.82873739308057 - type: precision value: 76.27622452019234 - type: recall value: 81.76943699731903 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (jpn-eng) config: jpn-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 92.30000000000001 - type: f1 value: 90.29666666666665 - type: precision value: 89.40333333333334 - type: recall value: 92.30000000000001 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (csb-eng) config: csb-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 29.249011857707508 - type: f1 value: 24.561866096392947 - type: precision value: 23.356583740215456 - type: recall value: 29.249011857707508 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (xho-eng) config: xho-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 77.46478873239437 - type: f1 value: 73.23943661971832 - type: precision value: 71.66666666666667 - type: recall value: 77.46478873239437 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (orv-eng) config: orv-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 20.35928143712575 - type: f1 value: 15.997867865075824 - type: precision value: 14.882104658301346 - type: recall value: 20.35928143712575 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ind-eng) config: ind-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 92.2 - type: f1 value: 90.25999999999999 - type: precision value: 89.45333333333335 - type: recall value: 92.2 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (tuk-eng) config: tuk-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 23.15270935960591 - type: f1 value: 19.65673625772148 - type: precision value: 18.793705293464992 - type: recall value: 23.15270935960591 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (max-eng) config: max-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 59.154929577464785 - type: f1 value: 52.3868463305083 - type: precision value: 50.14938113529662 - type: recall value: 59.154929577464785 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (swh-eng) config: swh-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 70.51282051282051 - type: f1 value: 66.8089133089133 - type: precision value: 65.37645687645687 - type: recall value: 70.51282051282051 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (hin-eng) config: hin-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 94.6 - type: f1 value: 93 - type: precision value: 92.23333333333333 - type: recall value: 94.6 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (dsb-eng) config: dsb-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 38.62212943632568 - type: f1 value: 34.3278276962583 - type: precision value: 33.07646935732408 - type: recall value: 38.62212943632568 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ber-eng) config: ber-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 28.1 - type: f1 value: 23.579609223054604 - type: precision value: 22.39622774921555 - type: recall value: 28.1 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (tam-eng) config: tam-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 88.27361563517914 - type: f1 value: 85.12486427795874 - type: precision value: 83.71335504885994 - type: recall value: 88.27361563517914 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (slk-eng) config: slk-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 88.6 - type: f1 value: 86.39928571428571 - type: precision value: 85.4947557997558 - type: recall value: 88.6 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (tgl-eng) config: tgl-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 86.5 - type: f1 value: 83.77952380952381 - type: precision value: 82.67602564102565 - type: recall value: 86.5 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ast-eng) config: ast-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 79.52755905511812 - type: f1 value: 75.3055868016498 - type: precision value: 73.81889763779527 - type: recall value: 79.52755905511812 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (mkd-eng) config: mkd-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 77.9 - type: f1 value: 73.76261904761905 - type: precision value: 72.11670995670995 - type: recall value: 77.9 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (khm-eng) config: khm-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 53.8781163434903 - type: f1 value: 47.25804051288816 - type: precision value: 45.0603482390186 - type: recall value: 53.8781163434903 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ces-eng) config: ces-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 91.10000000000001 - type: f1 value: 88.88 - type: precision value: 87.96333333333334 - type: recall value: 91.10000000000001 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (tzl-eng) config: tzl-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 38.46153846153847 - type: f1 value: 34.43978243978244 - type: precision value: 33.429487179487175 - type: recall value: 38.46153846153847 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (urd-eng) config: urd-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 88.9 - type: f1 value: 86.19888888888887 - type: precision value: 85.07440476190476 - type: recall value: 88.9 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (ara-eng) config: ara-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 85.9 - type: f1 value: 82.58857142857143 - type: precision value: 81.15666666666667 - type: recall value: 85.9 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (kor-eng) config: kor-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 86.8 - type: f1 value: 83.36999999999999 - type: precision value: 81.86833333333333 - type: recall value: 86.8 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (yid-eng) config: yid-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 68.51415094339622 - type: f1 value: 63.195000099481234 - type: precision value: 61.394033442972116 - type: recall value: 68.51415094339622 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (fin-eng) config: fin-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 88.5 - type: f1 value: 86.14603174603175 - type: precision value: 85.1162037037037 - type: recall value: 88.5 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (tha-eng) config: tha-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 95.62043795620438 - type: f1 value: 94.40389294403892 - type: precision value: 93.7956204379562 - type: recall value: 95.62043795620438 - task: type: BitextMining dataset: type: mteb/tatoeba-bitext-mining name: MTEB Tatoeba (wuu-eng) config: wuu-eng split: test revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553 metrics: - type: accuracy value: 81.8 - type: f1 value: 78.6532178932179 - type: precision value: 77.46348795840176 - type: recall value: 81.8 - task: type: Retrieval dataset: type: webis-touche2020 name: MTEB Touche2020 config: default split: test revision: None metrics: - type: map_at_1 value: 2.603 - type: map_at_10 value: 8.5 - type: map_at_100 value: 12.985 - type: map_at_1000 value: 14.466999999999999 - type: map_at_3 value: 4.859999999999999 - type: map_at_5 value: 5.817 - type: mrr_at_1 value: 28.571 - type: mrr_at_10 value: 42.331 - type: mrr_at_100 value: 43.592999999999996 - type: mrr_at_1000 value: 43.592999999999996 - type: mrr_at_3 value: 38.435 - type: mrr_at_5 value: 39.966 - type: ndcg_at_1 value: 26.531 - type: ndcg_at_10 value: 21.353 - type: ndcg_at_100 value: 31.087999999999997 - type: ndcg_at_1000 value: 43.163000000000004 - type: ndcg_at_3 value: 22.999 - type: ndcg_at_5 value: 21.451 - type: precision_at_1 value: 28.571 - type: precision_at_10 value: 19.387999999999998 - type: precision_at_100 value: 6.265 - type: precision_at_1000 value: 1.4160000000000001 - type: precision_at_3 value: 24.490000000000002 - type: precision_at_5 value: 21.224 - type: recall_at_1 value: 2.603 - type: recall_at_10 value: 14.474 - type: recall_at_100 value: 40.287 - type: recall_at_1000 value: 76.606 - type: recall_at_3 value: 5.978 - type: recall_at_5 value: 7.819 - task: type: Classification dataset: type: mteb/toxic_conversations_50k name: MTEB ToxicConversationsClassification config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 69.7848 - type: ap value: 13.661023167088224 - type: f1 value: 53.61686134460943 - task: type: Classification dataset: type: mteb/tweet_sentiment_extraction name: MTEB TweetSentimentExtractionClassification config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 61.28183361629882 - type: f1 value: 61.55481034919965 - task: type: Clustering dataset: type: mteb/twentynewsgroups-clustering name: MTEB TwentyNewsgroupsClustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 35.972128420092396 - task: type: PairClassification dataset: type: mteb/twittersemeval2015-pairclassification name: MTEB TwitterSemEval2015 config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 85.59933241938367 - type: cos_sim_ap value: 72.20760361208136 - type: cos_sim_f1 value: 66.4447731755424 - type: cos_sim_precision value: 62.35539102267469 - type: cos_sim_recall value: 71.10817941952506 - type: dot_accuracy value: 78.98313166835548 - type: dot_ap value: 44.492521645493795 - type: dot_f1 value: 45.814889336016094 - type: dot_precision value: 37.02439024390244 - type: dot_recall value: 60.07915567282321 - type: euclidean_accuracy value: 85.3907134767837 - type: euclidean_ap value: 71.53847289080343 - type: euclidean_f1 value: 65.95952206778834 - type: euclidean_precision value: 61.31006346328196 - type: euclidean_recall value: 71.37203166226914 - type: manhattan_accuracy value: 85.40859510043511 - type: manhattan_ap value: 71.49664104395515 - type: manhattan_f1 value: 65.98569969356485 - type: manhattan_precision value: 63.928748144482924 - type: manhattan_recall value: 68.17941952506597 - type: max_accuracy value: 85.59933241938367 - type: max_ap value: 72.20760361208136 - type: max_f1 value: 66.4447731755424 - task: type: PairClassification dataset: type: mteb/twitterurlcorpus-pairclassification name: MTEB TwitterURLCorpus config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 88.83261536073273 - type: cos_sim_ap value: 85.48178133644264 - type: cos_sim_f1 value: 77.87816307403935 - type: cos_sim_precision value: 75.88953021114926 - type: cos_sim_recall value: 79.97382198952879 - type: dot_accuracy value: 79.76287499514883 - type: dot_ap value: 59.17438838475084 - type: dot_f1 value: 56.34566667855996 - type: dot_precision value: 52.50349092359864 - type: dot_recall value: 60.794579611949494 - type: euclidean_accuracy value: 88.76857996662397 - type: euclidean_ap value: 85.22764834359887 - type: euclidean_f1 value: 77.65379751543554 - type: euclidean_precision value: 75.11152683839401 - type: euclidean_recall value: 80.37419156144134 - type: manhattan_accuracy value: 88.6987231730508 - type: manhattan_ap value: 85.18907981724007 - type: manhattan_f1 value: 77.51967028849757 - type: manhattan_precision value: 75.49992701795358 - type: manhattan_recall value: 79.65044656606098 - type: max_accuracy value: 88.83261536073273 - type: max_ap value: 85.48178133644264 - type: max_f1 value: 77.87816307403935 language: - multilingual - af - am - ar - as - az - be - bg - bn - br - bs - ca - cs - cy - da - de - el - en - eo - es - et - eu - fa - fi - fr - fy - ga - gd - gl - gu - ha - he - hi - hr - hu - hy - id - is - it - ja - jv - ka - kk - km - kn - ko - ku - ky - la - lo - lt - lv - mg - mk - ml - mn - mr - ms - my - ne - nl - 'no' - om - or - pa - pl - ps - pt - ro - ru - sa - sd - si - sk - sl - so - sq - sr - su - sv - sw - ta - te - th - tl - tr - ug - uk - ur - uz - vi - xh - yi - zh license: mit --- ## Multilingual-E5-base [Multilingual E5 Text Embeddings: A Technical Report](https://arxiv.org/pdf/2402.05672). Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024 This model has 12 layers and the embedding size is 768. ## Usage Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset. ```python import torch.nn.functional as F from torch import Tensor from transformers import AutoTokenizer, AutoModel def average_pool(last_hidden_states: Tensor, attention_mask: Tensor) -> Tensor: last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0) return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None] # Each input text should start with "query: " or "passage: ", even for non-English texts. # For tasks other than retrieval, you can simply use the "query: " prefix. input_texts = ['query: how much protein should a female eat', 'query: 南瓜的家常做法', "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.", "passage: 1.清炒南瓜丝 原料:嫩南瓜半个 调料:葱、盐、白糖、鸡精 做法: 1、南瓜用刀薄薄的削去表面一层皮,用勺子刮去瓤 2、擦成细丝(没有擦菜板就用刀慢慢切成细丝) 3、锅烧热放油,入葱花煸出香味 4、入南瓜丝快速翻炒一分钟左右,放盐、一点白糖和鸡精调味出锅 2.香葱炒南瓜 原料:南瓜1只 调料:香葱、蒜末、橄榄油、盐 做法: 1、将南瓜去皮,切成片 2、油锅8成热后,将蒜末放入爆香 3、爆香后,将南瓜片放入,翻炒 4、在翻炒的同时,可以不时地往锅里加水,但不要太多 5、放入盐,炒匀 6、南瓜差不多软和绵了之后,就可以关火 7、撒入香葱,即可出锅"] tokenizer = AutoTokenizer.from_pretrained('intfloat/multilingual-e5-base') model = AutoModel.from_pretrained('intfloat/multilingual-e5-base') # Tokenize the input texts batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt') outputs = model(**batch_dict) embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask']) # normalize embeddings embeddings = F.normalize(embeddings, p=2, dim=1) scores = (embeddings[:2] @ embeddings[2:].T) * 100 print(scores.tolist()) ``` ## Supported Languages This model is initialized from [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) and continually trained on a mixture of multilingual datasets. It supports 100 languages from xlm-roberta, but low-resource languages may see performance degradation. ## Training Details **Initialization**: [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) **First stage**: contrastive pre-training with weak supervision | Dataset | Weak supervision | # of text pairs | |--------------------------------------------------------------------------------------------------------|---------------------------------------|-----------------| | Filtered [mC4](https://huggingface.co/datasets/mc4) | (title, page content) | 1B | | [CC News](https://huggingface.co/datasets/intfloat/multilingual_cc_news) | (title, news content) | 400M | | [NLLB](https://huggingface.co/datasets/allenai/nllb) | translation pairs | 2.4B | | [Wikipedia](https://huggingface.co/datasets/intfloat/wikipedia) | (hierarchical section title, passage) | 150M | | Filtered [Reddit](https://www.reddit.com/) | (comment, response) | 800M | | [S2ORC](https://github.com/allenai/s2orc) | (title, abstract) and citation pairs | 100M | | [Stackexchange](https://stackexchange.com/) | (question, answer) | 50M | | [xP3](https://huggingface.co/datasets/bigscience/xP3) | (input prompt, response) | 80M | | [Miscellaneous unsupervised SBERT data](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) | - | 10M | **Second stage**: supervised fine-tuning | Dataset | Language | # of text pairs | |----------------------------------------------------------------------------------------|--------------|-----------------| | [MS MARCO](https://microsoft.github.io/msmarco/) | English | 500k | | [NQ](https://github.com/facebookresearch/DPR) | English | 70k | | [Trivia QA](https://github.com/facebookresearch/DPR) | English | 60k | | [NLI from SimCSE](https://github.com/princeton-nlp/SimCSE) | English | <300k | | [ELI5](https://huggingface.co/datasets/eli5) | English | 500k | | [DuReader Retrieval](https://github.com/baidu/DuReader/tree/master/DuReader-Retrieval) | Chinese | 86k | | [KILT Fever](https://huggingface.co/datasets/kilt_tasks) | English | 70k | | [KILT HotpotQA](https://huggingface.co/datasets/kilt_tasks) | English | 70k | | [SQuAD](https://huggingface.co/datasets/squad) | English | 87k | | [Quora](https://huggingface.co/datasets/quora) | English | 150k | | [Mr. TyDi](https://huggingface.co/datasets/castorini/mr-tydi) | 11 languages | 50k | | [MIRACL](https://huggingface.co/datasets/miracl/miracl) | 16 languages | 40k | For all labeled datasets, we only use its training set for fine-tuning. For other training details, please refer to our paper at [https://arxiv.org/pdf/2402.05672](https://arxiv.org/pdf/2402.05672). ## Benchmark Results on [Mr. TyDi](https://arxiv.org/abs/2108.08787) | Model | Avg MRR@10 | | ar | bn | en | fi | id | ja | ko | ru | sw | te | th | |-----------------------|------------|-------|------| --- | --- | --- | --- | --- | --- | --- |------| --- | --- | | BM25 | 33.3 | | 36.7 | 41.3 | 15.1 | 28.8 | 38.2 | 21.7 | 28.1 | 32.9 | 39.6 | 42.4 | 41.7 | | mDPR | 16.7 | | 26.0 | 25.8 | 16.2 | 11.3 | 14.6 | 18.1 | 21.9 | 18.5 | 7.3 | 10.6 | 13.5 | | BM25 + mDPR | 41.7 | | 49.1 | 53.5 | 28.4 | 36.5 | 45.5 | 35.5 | 36.2 | 42.7 | 40.5 | 42.0 | 49.2 | | | | | multilingual-e5-small | 64.4 | | 71.5 | 66.3 | 54.5 | 57.7 | 63.2 | 55.4 | 54.3 | 60.8 | 65.4 | 89.1 | 70.1 | | multilingual-e5-base | 65.9 | | 72.3 | 65.0 | 58.5 | 60.8 | 64.9 | 56.6 | 55.8 | 62.7 | 69.0 | 86.6 | 72.7 | | multilingual-e5-large | **70.5** | | 77.5 | 73.2 | 60.8 | 66.8 | 68.5 | 62.5 | 61.6 | 65.8 | 72.7 | 90.2 | 76.2 | ## MTEB Benchmark Evaluation Check out [unilm/e5](https://github.com/microsoft/unilm/tree/master/e5) to reproduce evaluation results on the [BEIR](https://arxiv.org/abs/2104.08663) and [MTEB benchmark](https://arxiv.org/abs/2210.07316). ## Support for Sentence Transformers Below is an example for usage with sentence_transformers. ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer('intfloat/multilingual-e5-base') input_texts = [ 'query: how much protein should a female eat', 'query: 南瓜的家常做法', "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 i s 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or traini ng for a marathon. Check out the chart below to see how much protein you should be eating each day.", "passage: 1.清炒南瓜丝 原料:嫩南瓜半个 调料:葱、盐、白糖、鸡精 做法: 1、南瓜用刀薄薄的削去表面一层皮 ,用勺子刮去瓤 2、擦成细丝(没有擦菜板就用刀慢慢切成细丝) 3、锅烧热放油,入葱花煸出香味 4、入南瓜丝快速翻炒一分钟左右, 放盐、一点白糖和鸡精调味出锅 2.香葱炒南瓜 原料:南瓜1只 调料:香葱、蒜末、橄榄油、盐 做法: 1、将南瓜去皮,切成片 2、油 锅8成热后,将蒜末放入爆香 3、爆香后,将南瓜片放入,翻炒 4、在翻炒的同时,可以不时地往锅里加水,但不要太多 5、放入盐,炒匀 6、南瓜差不多软和绵了之后,就可以关火 7、撒入香葱,即可出锅" ] embeddings = model.encode(input_texts, normalize_embeddings=True) ``` Package requirements `pip install sentence_transformers~=2.2.2` Contributors: [michaelfeil](https://huggingface.co/michaelfeil) ## FAQ **1. Do I need to add the prefix "query: " and "passage: " to input texts?** Yes, this is how the model is trained, otherwise you will see a performance degradation. Here are some rules of thumb: - Use "query: " and "passage: " correspondingly for asymmetric tasks such as passage retrieval in open QA, ad-hoc information retrieval. - Use "query: " prefix for symmetric tasks such as semantic similarity, bitext mining, paraphrase retrieval. - Use "query: " prefix if you want to use embeddings as features, such as linear probing classification, clustering. **2. Why are my reproduced results slightly different from reported in the model card?** Different versions of `transformers` and `pytorch` could cause negligible but non-zero performance differences. **3. Why does the cosine similarity scores distribute around 0.7 to 1.0?** This is a known and expected behavior as we use a low temperature 0.01 for InfoNCE contrastive loss. For text embedding tasks like text retrieval or semantic similarity, what matters is the relative order of the scores instead of the absolute values, so this should not be an issue. ## Citation If you find our paper or models helpful, please consider cite as follows: ``` @article{wang2024multilingual, title={Multilingual E5 Text Embeddings: A Technical Report}, author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu}, journal={arXiv preprint arXiv:2402.05672}, year={2024} } ``` ## Limitations Long texts will be truncated to at most 512 tokens.

google-bert/bert-base-multilingual-uncased

google-bert

transformers

fill-mask

--- language: - multilingual - af - sq - ar - an - hy - ast - az - ba - eu - bar - be - bn - inc - bs - br - bg - my - ca - ceb - ce - zh - cv - hr - cs - da - nl - en - et - fi - fr - gl - ka - de - el - gu - ht - he - hi - hu - is - io - id - ga - it - ja - jv - kn - kk - ky - ko - la - lv - lt - roa - nds - lm - mk - mg - ms - ml - mr - min - ne - new - nb - nn - oc - fa - pms - pl - pt - pa - ro - ru - sco - sr - hr - scn - sk - sl - aze - es - su - sw - sv - tl - tg - ta - tt - te - tr - uk - ud - uz - vi - vo - war - cy - fry - pnb - yo license: apache-2.0 datasets: - wikipedia --- # BERT multilingual base model (uncased) Pretrained model on the top 102 languages with the largest Wikipedia using a masked language modeling (MLM) objective. It was introduced in [this paper](https://arxiv.org/abs/1810.04805) and first released in [this repository](https://github.com/google-research/bert). This model is uncased: it does not make a difference between english and English. Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description BERT is a transformers model pretrained on a large corpus of multilingual data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was pretrained with two objectives: - Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence. - Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to predict if the two sentences were following each other or not. This way, the model learns an inner representation of the languages in the training set that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard classifier using the features produced by the BERT model as inputs. ## Intended uses & limitations You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=bert) to look for fine-tuned versions on a task that interests you. Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering. For tasks such as text generation you should look at model like GPT2. ### How to use You can use this model directly with a pipeline for masked language modeling: ```python >>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='bert-base-multilingual-uncased') >>> unmasker("Hello I'm a [MASK] model.") [{'sequence': "[CLS] hello i'm a top model. [SEP]", 'score': 0.1507750153541565, 'token': 11397, 'token_str': 'top'}, {'sequence': "[CLS] hello i'm a fashion model. [SEP]", 'score': 0.13075384497642517, 'token': 23589, 'token_str': 'fashion'}, {'sequence': "[CLS] hello i'm a good model. [SEP]", 'score': 0.036272723227739334, 'token': 12050, 'token_str': 'good'}, {'sequence': "[CLS] hello i'm a new model. [SEP]", 'score': 0.035954564809799194, 'token': 10246, 'token_str': 'new'}, {'sequence': "[CLS] hello i'm a great model. [SEP]", 'score': 0.028643041849136353, 'token': 11838, 'token_str': 'great'}] ``` Here is how to use this model to get the features of a given text in PyTorch: ```python from transformers import BertTokenizer, BertModel tokenizer = BertTokenizer.from_pretrained('bert-base-multilingual-uncased') model = BertModel.from_pretrained("bert-base-multilingual-uncased") text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='pt') output = model(**encoded_input) ``` and in TensorFlow: ```python from transformers import BertTokenizer, TFBertModel tokenizer = BertTokenizer.from_pretrained('bert-base-multilingual-uncased') model = TFBertModel.from_pretrained("bert-base-multilingual-uncased") text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='tf') output = model(encoded_input) ``` ### Limitations and bias Even if the training data used for this model could be characterized as fairly neutral, this model can have biased predictions: ```python >>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='bert-base-multilingual-uncased') >>> unmasker("The man worked as a [MASK].") [{'sequence': '[CLS] the man worked as a teacher. [SEP]', 'score': 0.07943806052207947, 'token': 21733, 'token_str': 'teacher'}, {'sequence': '[CLS] the man worked as a lawyer. [SEP]', 'score': 0.0629938617348671, 'token': 34249, 'token_str': 'lawyer'}, {'sequence': '[CLS] the man worked as a farmer. [SEP]', 'score': 0.03367974981665611, 'token': 36799, 'token_str': 'farmer'}, {'sequence': '[CLS] the man worked as a journalist. [SEP]', 'score': 0.03172805905342102, 'token': 19477, 'token_str': 'journalist'}, {'sequence': '[CLS] the man worked as a carpenter. [SEP]', 'score': 0.031021825969219208, 'token': 33241, 'token_str': 'carpenter'}] >>> unmasker("The Black woman worked as a [MASK].") [{'sequence': '[CLS] the black woman worked as a nurse. [SEP]', 'score': 0.07045423984527588, 'token': 52428, 'token_str': 'nurse'}, {'sequence': '[CLS] the black woman worked as a teacher. [SEP]', 'score': 0.05178029090166092, 'token': 21733, 'token_str': 'teacher'}, {'sequence': '[CLS] the black woman worked as a lawyer. [SEP]', 'score': 0.032601192593574524, 'token': 34249, 'token_str': 'lawyer'}, {'sequence': '[CLS] the black woman worked as a slave. [SEP]', 'score': 0.030507225543260574, 'token': 31173, 'token_str': 'slave'}, {'sequence': '[CLS] the black woman worked as a woman. [SEP]', 'score': 0.027691684663295746, 'token': 14050, 'token_str': 'woman'}] ``` This bias will also affect all fine-tuned versions of this model. ## Training data The BERT model was pretrained on the 102 languages with the largest Wikipedias. You can find the complete list [here](https://github.com/google-research/bert/blob/master/multilingual.md#list-of-languages). ## Training procedure ### Preprocessing The texts are lowercased and tokenized using WordPiece and a shared vocabulary size of 110,000. The languages with a larger Wikipedia are under-sampled and the ones with lower resources are oversampled. For languages like Chinese, Japanese Kanji and Korean Hanja that don't have space, a CJK Unicode block is added around every character. The inputs of the model are then of the form: ``` [CLS] Sentence A [SEP] Sentence B [SEP] ``` With probability 0.5, sentence A and sentence B correspond to two consecutive sentences in the original corpus and in the other cases, it's another random sentence in the corpus. Note that what is considered a sentence here is a consecutive span of text usually longer than a single sentence. The only constrain is that the result with the two "sentences" has a combined length of less than 512 tokens. The details of the masking procedure for each sentence are the following: - 15% of the tokens are masked. - In 80% of the cases, the masked tokens are replaced by `[MASK]`. - In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace. - In the 10% remaining cases, the masked tokens are left as is. ### BibTeX entry and citation info ```bibtex @article{DBLP:journals/corr/abs-1810-04805, author = {Jacob Devlin and Ming{-}Wei Chang and Kenton Lee and Kristina Toutanova}, title = {{BERT:} Pre-training of Deep Bidirectional Transformers for Language Understanding}, journal = {CoRR}, volume = {abs/1810.04805}, year = {2018}, url = {http://arxiv.org/abs/1810.04805}, archivePrefix = {arXiv}, eprint = {1810.04805}, timestamp = {Tue, 30 Oct 2018 20:39:56 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1810-04805.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ```

TinyLlama/TinyLlama-1.1B-Chat-v1.0

TinyLlama

transformers

text-generation

--- license: apache-2.0 datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata - HuggingFaceH4/ultrachat_200k - HuggingFaceH4/ultrafeedback_binarized language: - en widget: - example_title: Fibonacci (Python) messages: - role: system content: You are a chatbot who can help code! - role: user content: Write me a function to calculate the first 10 digits of the fibonacci sequence in Python and print it out to the CLI. --- <div align="center"> # TinyLlama-1.1B </div> https://github.com/jzhang38/TinyLlama The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint. #### This Model This is the chat model finetuned on top of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T). **We follow [HF's Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha)'s training recipe.** The model was " initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4." #### How to use You will need the transformers>=4.34 Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information. ```python # Install transformers from source - only needed for versions <= v4.34 # pip install git+https://github.com/huggingface/transformers.git # pip install accelerate import torch from transformers import pipeline pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.bfloat16, device_map="auto") # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating messages = [ { "role": "system", "content": "You are a friendly chatbot who always responds in the style of a pirate", }, {"role": "user", "content": "How many helicopters can a human eat in one sitting?"}, ] prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) # <|system|> # You are a friendly chatbot who always responds in the style of a pirate.</s> # <|user|> # How many helicopters can a human eat in one sitting?</s> # <|assistant|> # ... ```

yiyanghkust/finbert-tone

yiyanghkust

transformers

text-classification

--- language: "en" tags: - financial-sentiment-analysis - sentiment-analysis widget: - text: "growth is strong and we have plenty of liquidity" --- `FinBERT` is a BERT model pre-trained on financial communication text. The purpose is to enhance financial NLP research and practice. It is trained on the following three financial communication corpus. The total corpora size is 4.9B tokens. - Corporate Reports 10-K & 10-Q: 2.5B tokens - Earnings Call Transcripts: 1.3B tokens - Analyst Reports: 1.1B tokens More technical details on `FinBERT`: [Click Link](https://github.com/yya518/FinBERT) This released `finbert-tone` model is the `FinBERT` model fine-tuned on 10,000 manually annotated (positive, negative, neutral) sentences from analyst reports. This model achieves superior performance on financial tone analysis task. If you are simply interested in using `FinBERT` for financial tone analysis, give it a try. If you use the model in your academic work, please cite the following paper: Huang, Allen H., Hui Wang, and Yi Yang. "FinBERT: A Large Language Model for Extracting Information from Financial Text." *Contemporary Accounting Research* (2022). # How to use You can use this model with Transformers pipeline for sentiment analysis. ```python from transformers import BertTokenizer, BertForSequenceClassification from transformers import pipeline finbert = BertForSequenceClassification.from_pretrained('yiyanghkust/finbert-tone',num_labels=3) tokenizer = BertTokenizer.from_pretrained('yiyanghkust/finbert-tone') nlp = pipeline("sentiment-analysis", model=finbert, tokenizer=tokenizer) sentences = ["there is a shortage of capital, and we need extra financing", "growth is strong and we have plenty of liquidity", "there are doubts about our finances", "profits are flat"] results = nlp(sentences) print(results) #LABEL_0: neutral; LABEL_1: positive; LABEL_2: negative ```

sadickam/sdg-classification-bert

sadickam

transformers

text-classification

--- license: mit language: - en metrics: - accuracy - matthews_correlation widget: - text: "Highway work zones create potential risks for both traffic and workers in addition to traffic congestion and delays that result in increased road user delay." - text: "A circular economy is a way of achieving sustainable consumption and production, as well as nature positive outcomes." --- # sadickam/sdg-classification-bert <!-- Provide a quick summary of what the model is/does. --> This model (sgdBERT) is for classifying text with respect to the United Nations sustainable development goals (SDG).  Source:https://www.un.org/development/desa/disabilities/about-us/sustainable-development-goals-sdgs-and-disability.html ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This text classification model was developed by fine-tuning the bert-base-uncased pre-trained model. The training data for this fine-tuned model was sourced from the publicly available OSDG Community Dataset (OSDG-CD) at https://zenodo.org/record/5550238#.ZBulfcJByF4. This model was made as part of academic research at Deakin University. The goal was to make a transformer-based SDG text classification model that anyone could use. Only the first 16 UN SDGs supported. The primary model details are highlighted below: - **Model type:** Text classification - **Language(s) (NLP):** English - **License:** mit - **Finetuned from model [optional]:** bert-base-uncased ### Model Sources <!-- Provide the basic links for the model. --> - **Repository:** https://huggingface.co/sadickam/sdg-classification-bert - **Demo [optional]:** option 1: https://sadickam-sdg-text-classifier.hf.space/; option 2: https://sadickam-sdg-classification-bert-main-qxg1gv.streamlit.app/ ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> This is a fine-tuned model and therefore requires no further training. ## How to Get Started with the Model Use the code below to get started with the model. ```python from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("sadickam/sdg-classification-bert") model = AutoModelForSequenceClassification.from_pretrained("sadickam/sdg-classification-bert") ``` ## Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> The training data includes text from a wide range of industries and academic research fields. Hence, this fine-tuned model is not for a specific industry. See training here: https://zenodo.org/record/5550238#.ZBulfcJByF4 ## Training Hyperparameters - Num_epoch = 3 - Learning rate = 5e-5 - Batch size = 16 ## Evaluation #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> - Accuracy = 0.90 - Matthews correlation = 0.89 ## Citation Sadick, A.M. (2023). SDG classification with BERT. https://huggingface.co/sadickam/sdg-classification-bert <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> ## Model Card Contact s.sadick@deakin.edu.au

h94/IP-Adapter-FaceID

h94

diffusers

text-to-image

--- tags: - text-to-image - stable-diffusion language: - en library_name: diffusers --- # IP-Adapter-FaceID Model Card <div align="center"> [**Project Page**](https://ip-adapter.github.io) **|** [**Paper (ArXiv)**](https://arxiv.org/abs/2308.06721) **|** [**Code**](https://github.com/tencent-ailab/IP-Adapter) </div> --- ## Introduction An experimental version of IP-Adapter-FaceID: we use face ID embedding from a face recognition model instead of CLIP image embedding, additionally, we use LoRA to improve ID consistency. IP-Adapter-FaceID can generate various style images conditioned on a face with only text prompts.  **Update 2023/12/27**: IP-Adapter-FaceID-Plus: face ID embedding (for face ID) + CLIP image embedding (for face structure) <div align="center">  </div> **Update 2023/12/28**: IP-Adapter-FaceID-PlusV2: face ID embedding (for face ID) + controllable CLIP image embedding (for face structure) You can adjust the weight of the face structure to get different generation! <div align="center">  </div> **Update 2024/01/04**: IP-Adapter-FaceID-SDXL: An experimental SDXL version of IP-Adapter-FaceID <div align="center">  </div> **Update 2024/01/17**: IP-Adapter-FaceID-PlusV2-SDXL: An experimental SDXL version of IP-Adapter-FaceID-PlusV2 **Update 2024/01/19**: IP-Adapter-FaceID-Portrait: same with IP-Adapter-FaceID but for portrait generation (no lora! no controlnet!). Specifically, it accepts multiple facial images to enhance similarity (the default is 5). <div align="center">  </div> ## Usage ### IP-Adapter-FaceID Firstly, you should use [insightface](https://github.com/deepinsight/insightface) to extract face ID embedding: ```python import cv2 from insightface.app import FaceAnalysis import torch app = FaceAnalysis(name="buffalo_l", providers=['CUDAExecutionProvider', 'CPUExecutionProvider']) app.prepare(ctx_id=0, det_size=(640, 640)) image = cv2.imread("person.jpg") faces = app.get(image) faceid_embeds = torch.from_numpy(faces[0].normed_embedding).unsqueeze(0) ``` Then, you can generate images conditioned on the face embeddings: ```python import torch from diffusers import StableDiffusionPipeline, DDIMScheduler, AutoencoderKL from PIL import Image from ip_adapter.ip_adapter_faceid import IPAdapterFaceID base_model_path = "SG161222/Realistic_Vision_V4.0_noVAE" vae_model_path = "stabilityai/sd-vae-ft-mse" ip_ckpt = "ip-adapter-faceid_sd15.bin" device = "cuda" noise_scheduler = DDIMScheduler( num_train_timesteps=1000, beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", clip_sample=False, set_alpha_to_one=False, steps_offset=1, ) vae = AutoencoderKL.from_pretrained(vae_model_path).to(dtype=torch.float16) pipe = StableDiffusionPipeline.from_pretrained( base_model_path, torch_dtype=torch.float16, scheduler=noise_scheduler, vae=vae, feature_extractor=None, safety_checker=None ) # load ip-adapter ip_model = IPAdapterFaceID(pipe, ip_ckpt, device) # generate image prompt = "photo of a woman in red dress in a garden" negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality, blurry" images = ip_model.generate( prompt=prompt, negative_prompt=negative_prompt, faceid_embeds=faceid_embeds, num_samples=4, width=512, height=768, num_inference_steps=30, seed=2023 ) ``` you can also use a normal IP-Adapter and a normal LoRA to load model: ```python import torch from diffusers import StableDiffusionPipeline, DDIMScheduler, AutoencoderKL from PIL import Image from ip_adapter.ip_adapter_faceid_separate import IPAdapterFaceID base_model_path = "SG161222/Realistic_Vision_V4.0_noVAE" vae_model_path = "stabilityai/sd-vae-ft-mse" ip_ckpt = "ip-adapter-faceid_sd15.bin" lora_ckpt = "ip-adapter-faceid_sd15_lora.safetensors" device = "cuda" noise_scheduler = DDIMScheduler( num_train_timesteps=1000, beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", clip_sample=False, set_alpha_to_one=False, steps_offset=1, ) vae = AutoencoderKL.from_pretrained(vae_model_path).to(dtype=torch.float16) pipe = StableDiffusionPipeline.from_pretrained( base_model_path, torch_dtype=torch.float16, scheduler=noise_scheduler, vae=vae, feature_extractor=None, safety_checker=None ) # load lora and fuse pipe.load_lora_weights(lora_ckpt) pipe.fuse_lora() # load ip-adapter ip_model = IPAdapterFaceID(pipe, ip_ckpt, device) # generate image prompt = "photo of a woman in red dress in a garden" negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality, blurry" images = ip_model.generate( prompt=prompt, negative_prompt=negative_prompt, faceid_embeds=faceid_embeds, num_samples=4, width=512, height=768, num_inference_steps=30, seed=2023 ) ``` ### IP-Adapter-FaceID-SDXL Firstly, you should use [insightface](https://github.com/deepinsight/insightface) to extract face ID embedding: ```python import cv2 from insightface.app import FaceAnalysis import torch app = FaceAnalysis(name="buffalo_l", providers=['CUDAExecutionProvider', 'CPUExecutionProvider']) app.prepare(ctx_id=0, det_size=(640, 640)) image = cv2.imread("person.jpg") faces = app.get(image) faceid_embeds = torch.from_numpy(faces[0].normed_embedding).unsqueeze(0) ``` Then, you can generate images conditioned on the face embeddings: ```python import torch from diffusers import StableDiffusionXLPipeline, DDIMScheduler from PIL import Image from ip_adapter.ip_adapter_faceid import IPAdapterFaceIDXL base_model_path = "SG161222/RealVisXL_V3.0" ip_ckpt = "ip-adapter-faceid_sdxl.bin" device = "cuda" noise_scheduler = DDIMScheduler( num_train_timesteps=1000, beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", clip_sample=False, set_alpha_to_one=False, steps_offset=1, ) pipe = StableDiffusionXLPipeline.from_pretrained( base_model_path, torch_dtype=torch.float16, scheduler=noise_scheduler, add_watermarker=False, ) # load ip-adapter ip_model = IPAdapterFaceIDXL(pipe, ip_ckpt, device) # generate image prompt = "A closeup shot of a beautiful Asian teenage girl in a white dress wearing small silver earrings in the garden, under the soft morning light" negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality, blurry" images = ip_model.generate( prompt=prompt, negative_prompt=negative_prompt, faceid_embeds=faceid_embeds, num_samples=2, width=1024, height=1024, num_inference_steps=30, guidance_scale=7.5, seed=2023 ) ``` ### IP-Adapter-FaceID-Plus Firstly, you should use [insightface](https://github.com/deepinsight/insightface) to extract face ID embedding and face image: ```python import cv2 from insightface.app import FaceAnalysis from insightface.utils import face_align import torch app = FaceAnalysis(name="buffalo_l", providers=['CUDAExecutionProvider', 'CPUExecutionProvider']) app.prepare(ctx_id=0, det_size=(640, 640)) image = cv2.imread("person.jpg") faces = app.get(image) faceid_embeds = torch.from_numpy(faces[0].normed_embedding).unsqueeze(0) face_image = face_align.norm_crop(image, landmark=faces[0].kps, image_size=224) # you can also segment the face ``` Then, you can generate images conditioned on the face embeddings: ```python import torch from diffusers import StableDiffusionPipeline, DDIMScheduler, AutoencoderKL from PIL import Image from ip_adapter.ip_adapter_faceid import IPAdapterFaceIDPlus v2 = False base_model_path = "SG161222/Realistic_Vision_V4.0_noVAE" vae_model_path = "stabilityai/sd-vae-ft-mse" image_encoder_path = "laion/CLIP-ViT-H-14-laion2B-s32B-b79K" ip_ckpt = "ip-adapter-faceid-plus_sd15.bin" if not v2 else "ip-adapter-faceid-plusv2_sd15.bin" device = "cuda" noise_scheduler = DDIMScheduler( num_train_timesteps=1000, beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", clip_sample=False, set_alpha_to_one=False, steps_offset=1, ) vae = AutoencoderKL.from_pretrained(vae_model_path).to(dtype=torch.float16) pipe = StableDiffusionPipeline.from_pretrained( base_model_path, torch_dtype=torch.float16, scheduler=noise_scheduler, vae=vae, feature_extractor=None, safety_checker=None ) # load ip-adapter ip_model = IPAdapterFaceIDPlus(pipe, image_encoder_path, ip_ckpt, device) # generate image prompt = "photo of a woman in red dress in a garden" negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality, blurry" images = ip_model.generate( prompt=prompt, negative_prompt=negative_prompt, face_image=face_image, faceid_embeds=faceid_embeds, shortcut=v2, s_scale=1.0, num_samples=4, width=512, height=768, num_inference_steps=30, seed=2023 ) ``` ### IP-Adapter-FaceID-Portrait ```python import cv2 from insightface.app import FaceAnalysis import torch app = FaceAnalysis(name="buffalo_l", providers=['CUDAExecutionProvider', 'CPUExecutionProvider']) app.prepare(ctx_id=0, det_size=(640, 640)) images = ["1.jpg", "2.jpg", "3.jpg", "4.jpg", "5.jpg"] faceid_embeds = [] for image in images: image = cv2.imread("person.jpg") faces = app.get(image) faceid_embeds.append(torch.from_numpy(faces[0].normed_embedding).unsqueeze(0).unsqueeze(0)) faceid_embeds = torch.cat(faceid_embeds, dim=1) ``` ```python import torch from diffusers import StableDiffusionPipeline, DDIMScheduler, AutoencoderKL from PIL import Image from ip_adapter.ip_adapter_faceid_separate import IPAdapterFaceID base_model_path = "SG161222/Realistic_Vision_V4.0_noVAE" vae_model_path = "stabilityai/sd-vae-ft-mse" ip_ckpt = "ip-adapter-faceid-portrait_sd15.bin" device = "cuda" noise_scheduler = DDIMScheduler( num_train_timesteps=1000, beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", clip_sample=False, set_alpha_to_one=False, steps_offset=1, ) vae = AutoencoderKL.from_pretrained(vae_model_path).to(dtype=torch.float16) pipe = StableDiffusionPipeline.from_pretrained( base_model_path, torch_dtype=torch.float16, scheduler=noise_scheduler, vae=vae, feature_extractor=None, safety_checker=None ) # load ip-adapter ip_model = IPAdapterFaceID(pipe, ip_ckpt, device, num_tokens=16, n_cond=5) # generate image prompt = "photo of a woman in red dress in a garden" negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality, blurry" images = ip_model.generate( prompt=prompt, negative_prompt=negative_prompt, faceid_embeds=faceid_embeds, num_samples=4, width=512, height=512, num_inference_steps=30, seed=2023 ) ``` ## Limitations and Bias - The models do not achieve perfect photorealism and ID consistency. - The generalization of the models is limited due to limitations of the training data, base model and face recognition model. ## Non-commercial use **AS InsightFace pretrained models are available for non-commercial research purposes, IP-Adapter-FaceID models are released exclusively for research purposes and is not intended for commercial use.**

immich-app/ViT-B-32__openai

immich-app

transformers

--- tags: - immich - clip --- # Model Description This repo contains ONNX exports for the CLIP model [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32). It separates the visual and textual encoders into separate models for the purpose of generating image and text embeddings. This repo is specifically intended for use with [Immich](https://immich.app/), a self-hosted photo library.

obi/deid_roberta_i2b2

obi

transformers

token-classification

--- language: - en thumbnail: "https://www.onebraveidea.org/wp-content/uploads/2019/07/OBI-Logo-Website.png" tags: - deidentification - medical notes - ehr - phi datasets: - I2B2 metrics: - F1 - Recall - Precision widget: - text: "Physician Discharge Summary Admit date: 10/12/1982 Discharge date: 10/22/1982 Patient Information Jack Reacher, 54 y.o. male (DOB = 1/21/1928)." - text: "Home Address: 123 Park Drive, San Diego, CA, 03245. Home Phone: 202-555-0199 (home)." - text: "Hospital Care Team Service: Orthopedics Inpatient Attending: Roger C Kelly, MD Attending phys phone: (634)743-5135 Discharge Unit: HCS843 Primary Care Physician: Hassan V Kim, MD 512-832-5025." license: mit --- # Model Description * A RoBERTa [[Liu et al., 2019]](https://arxiv.org/pdf/1907.11692.pdf) model fine-tuned for de-identification of medical notes. * Sequence Labeling (token classification): The model was trained to predict protected health information (PHI/PII) entities (spans). A list of protected health information categories is given by [HIPAA](https://www.hhs.gov/hipaa/for-professionals/privacy/laws-regulations/index.html). * A token can either be classified as non-PHI or as one of the 11 PHI types. Token predictions are aggregated to spans by making use of BILOU tagging. * The PHI labels that were used for training and other details can be found here: [Annotation Guidelines](https://github.com/obi-ml-public/ehr_deidentification/blob/master/AnnotationGuidelines.md) * More details on how to use this model, the format of data and other useful information is present in the GitHub repo: [Robust DeID](https://github.com/obi-ml-public/ehr_deidentification). # How to use * A demo on how the model works (using model predictions to de-identify a medical note) is on this space: [Medical-Note-Deidentification](https://huggingface.co/spaces/obi/Medical-Note-Deidentification). * Steps on how this model can be used to run a forward pass can be found here: [Forward Pass](https://github.com/obi-ml-public/ehr_deidentification/tree/master/steps/forward_pass) * In brief, the steps are: * Sentencize (the model aggregates the sentences back to the note level) and tokenize the dataset. * Use the predict function of this model to gather the predictions (i.e., predictions for each token). * Additionally, the model predictions can be used to remove PHI from the original note/text. # Dataset * The I2B2 2014 [[Stubbs and Uzuner, 2015]](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4978170/) dataset was used to train this model. | | I2B2 | | I2B2 | | | --------- | --------------------- | ---------- | -------------------- | ---------- | | | TRAIN SET - 790 NOTES | | TEST SET - 514 NOTES | | | PHI LABEL | COUNT | PERCENTAGE | COUNT | PERCENTAGE | | DATE | 7502 | 43.69 | 4980 | 44.14 | | STAFF | 3149 | 18.34 | 2004 | 17.76 | | HOSP | 1437 | 8.37 | 875 | 7.76 | | AGE | 1233 | 7.18 | 764 | 6.77 | | LOC | 1206 | 7.02 | 856 | 7.59 | | PATIENT | 1316 | 7.66 | 879 | 7.79 | | PHONE | 317 | 1.85 | 217 | 1.92 | | ID | 881 | 5.13 | 625 | 5.54 | | PATORG | 124 | 0.72 | 82 | 0.73 | | EMAIL | 4 | 0.02 | 1 | 0.01 | | OTHERPHI | 2 | 0.01 | 0 | 0 | | TOTAL | 17171 | 100 | 11283 | 100 | # Training procedure * Steps on how this model was trained can be found here: [Training](https://github.com/obi-ml-public/ehr_deidentification/tree/master/steps/train). The "model_name_or_path" was set to: "roberta-large". * The dataset was sentencized with the en_core_sci_sm sentencizer from spacy. * The dataset was then tokenized with a custom tokenizer built on top of the en_core_sci_sm tokenizer from spacy. * For each sentence we added 32 tokens on the left (from previous sentences) and 32 tokens on the right (from the next sentences). * The added tokens are not used for learning - i.e, the loss is not computed on these tokens - they are used as additional context. * Each sequence contained a maximum of 128 tokens (including the 32 tokens added on). Longer sequences were split. * The sentencized and tokenized dataset with the token level labels based on the BILOU notation was used to train the model. * The model is fine-tuned from a pre-trained RoBERTa model. * Training details: * Input sequence length: 128 * Batch size: 32 (16 with 2 gradient accumulation steps) * Optimizer: AdamW * Learning rate: 5e-5 * Dropout: 0.1 ## Results # Questions? Post a Github issue on the repo: [Robust DeID](https://github.com/obi-ml-public/ehr_deidentification).

facebook/bart-base

facebook

transformers

feature-extraction

--- license: apache-2.0 language: en --- # BART (base-sized model) BART model pre-trained on English language. It was introduced in the paper [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://arxiv.org/abs/1910.13461) by Lewis et al. and first released in [this repository](https://github.com/pytorch/fairseq/tree/master/examples/bart). Disclaimer: The team releasing BART did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description BART is a transformer encoder-decoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. BART is particularly effective when fine-tuned for text generation (e.g. summarization, translation) but also works well for comprehension tasks (e.g. text classification, question answering). ## Intended uses & limitations You can use the raw model for text infilling. However, the model is mostly meant to be fine-tuned on a supervised dataset. See the [model hub](https://huggingface.co/models?search=bart) to look for fine-tuned versions on a task that interests you. ### How to use Here is how to use this model in PyTorch: ```python from transformers import BartTokenizer, BartModel tokenizer = BartTokenizer.from_pretrained('facebook/bart-base') model = BartModel.from_pretrained('facebook/bart-base') inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") outputs = model(**inputs) last_hidden_states = outputs.last_hidden_state ``` ### BibTeX entry and citation info ```bibtex @article{DBLP:journals/corr/abs-1910-13461, author = {Mike Lewis and Yinhan Liu and Naman Goyal and Marjan Ghazvininejad and Abdelrahman Mohamed and Omer Levy and Veselin Stoyanov and Luke Zettlemoyer}, title = {{BART:} Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension}, journal = {CoRR}, volume = {abs/1910.13461}, year = {2019}, url = {http://arxiv.org/abs/1910.13461}, eprinttype = {arXiv}, eprint = {1910.13461}, timestamp = {Thu, 31 Oct 2019 14:02:26 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1910-13461.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ```

pysentimiento/robertuito-emotion-analysis

pysentimiento

pysentimiento

--- language: - es library_name: pysentimiento tags: - emotion-analysis - twitter --- # Emotion Analysis in Spanish ## robertuito-emotion-analysis Repository: [https://github.com/pysentimiento/pysentimiento/](https://github.com/finiteautomata/pysentimiento/) Model trained with TASS 2020 Task 2 corpus for Emotion detection in Spanish. Base model is [RoBERTuito](https://github.com/pysentimiento/robertuito), a RoBERTa model trained in Spanish tweets. Contains the six Ekman emotions plus a neutral class: - anger - disgust - fear - joy - sadness - surprise ## Results Results for the four tasks evaluated in `pysentimiento`. Results are expressed as Macro F1 scores | model | emotion | hate_speech | irony | sentiment | |:--------------|:--------------|:--------------|:--------------|:--------------| | robertuito | 0.560 ± 0.010 | 0.759 ± 0.007 | 0.739 ± 0.005 | 0.705 ± 0.003 | | roberta | 0.527 ± 0.015 | 0.741 ± 0.012 | 0.721 ± 0.008 | 0.670 ± 0.006 | | bertin | 0.524 ± 0.007 | 0.738 ± 0.007 | 0.713 ± 0.012 | 0.666 ± 0.005 | | beto_uncased | 0.532 ± 0.012 | 0.727 ± 0.016 | 0.701 ± 0.007 | 0.651 ± 0.006 | | beto_cased | 0.516 ± 0.012 | 0.724 ± 0.012 | 0.705 ± 0.009 | 0.662 ± 0.005 | | mbert_uncased | 0.493 ± 0.010 | 0.718 ± 0.011 | 0.681 ± 0.010 | 0.617 ± 0.003 | | biGRU | 0.264 ± 0.007 | 0.592 ± 0.018 | 0.631 ± 0.011 | 0.585 ± 0.011 | Note that for Hate Speech, these are the results for Semeval 2019, Task 5 Subtask B (HS+TR+AG detection) ## Citation If you use this model in your research, please cite pysentimiento, RoBERTuito and EmoEvent papers: ``` @misc{perez2021pysentimiento, title={pysentimiento: A Python Toolkit for Sentiment Analysis and SocialNLP tasks}, author={Juan Manuel Pérez and Juan Carlos Giudici and Franco Luque}, year={2021}, eprint={2106.09462}, archivePrefix={arXiv}, primaryClass={cs.CL} } @inproceedings{del2020emoevent, title={EmoEvent: A multilingual emotion corpus based on different events}, author={del Arco, Flor Miriam Plaza and Strapparava, Carlo and Lopez, L Alfonso Urena and Mart{\'\i}n-Valdivia, M Teresa}, booktitle={Proceedings of the 12th Language Resources and Evaluation Conference}, pages={1492--1498}, year={2020} } @inproceedings{perez-etal-2022-robertuito, title = "{R}o{BERT}uito: a pre-trained language model for social media text in {S}panish", author = "P{\'e}rez, Juan Manuel and Furman, Dami{\'a}n Ariel and Alonso Alemany, Laura and Luque, Franco M.", booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference", month = jun, year = "2022", address = "Marseille, France", publisher = "European Language Resources Association", url = "https://aclanthology.org/2022.lrec-1.785", pages = "7235--7243", abstract = "Since BERT appeared, Transformer language models and transfer learning have become state-of-the-art for natural language processing tasks. Recently, some works geared towards pre-training specially-crafted models for particular domains, such as scientific papers, medical documents, user-generated texts, among others. These domain-specific models have been shown to improve performance significantly in most tasks; however, for languages other than English, such models are not widely available. In this work, we present RoBERTuito, a pre-trained language model for user-generated text in Spanish, trained on over 500 million tweets. Experiments on a benchmark of tasks involving user-generated text showed that RoBERTuito outperformed other pre-trained language models in Spanish. In addition to this, our model has some cross-lingual abilities, achieving top results for English-Spanish tasks of the Linguistic Code-Switching Evaluation benchmark (LinCE) and also competitive performance against monolingual models in English Twitter tasks. To facilitate further research, we make RoBERTuito publicly available at the HuggingFace model hub together with the dataset used to pre-train it.", } ```

medicalai/ClinicalBERT

medicalai

transformers

fill-mask

--- tags: - medical --- # ClinicalBERT <!-- Provide a quick summary of what the model is/does. --> This model card describes the ClinicalBERT model, which was trained on a large multicenter dataset with a large corpus of 1.2B words of diverse diseases we constructed. We then utilized a large-scale corpus of EHRs from over 3 million patient records to fine tune the base language model. ## Pretraining Data The ClinicalBERT model was trained on a large multicenter dataset with a large corpus of 1.2B words of diverse diseases we constructed. <!-- For more details, see here. --> ## Model Pretraining ### Pretraining Procedures The ClinicalBERT was initialized from BERT. Then the training followed the principle of masked language model, in which given a piece of text, we randomly replace some tokens by MASKs, special tokens for masking, and then require the model to predict the original tokens via contextual text. ### Pretraining Hyperparameters We used a batch size of 32, a maximum sequence length of 256, and a learning rate of 5e-5 for pre-training our models. ## How to use the model Load the model via the transformers library: ```python from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("medicalai/ClinicalBERT") model = AutoModel.from_pretrained("medicalai/ClinicalBERT") ``` ## Citation Please cite this article: Wang, G., Liu, X., Ying, Z. et al. Optimized glycemic control of type 2 diabetes with reinforcement learning: a proof-of-concept trial. Nat Med (2023). https://doi.org/10.1038/s41591-023-02552-9

nateraw/vit-age-classifier

nateraw

transformers

image-classification

--- tags: - image-classification - pytorch datasets: - nateraw/fairface --- A vision transformer finetuned to classify the age of a given person's face. ```python import requests from PIL import Image from io import BytesIO from transformers import ViTFeatureExtractor, ViTForImageClassification # Get example image from official fairface repo + read it in as an image r = requests.get('https://github.com/dchen236/FairFace/blob/master/detected_faces/race_Asian_face0.jpg?raw=true') im = Image.open(BytesIO(r.content)) # Init model, transforms model = ViTForImageClassification.from_pretrained('nateraw/vit-age-classifier') transforms = ViTFeatureExtractor.from_pretrained('nateraw/vit-age-classifier') # Transform our image and pass it through the model inputs = transforms(im, return_tensors='pt') output = model(**inputs) # Predicted Class probabilities proba = output.logits.softmax(1) # Predicted Classes preds = proba.argmax(1) ```

microsoft/layoutlmv3-base

microsoft

transformers

--- language: en license: cc-by-nc-sa-4.0 --- # LayoutLMv3 [Microsoft Document AI](https://www.microsoft.com/en-us/research/project/document-ai/) | [GitHub](https://aka.ms/layoutlmv3) ## Model description LayoutLMv3 is a pre-trained multimodal Transformer for Document AI with unified text and image masking. The simple unified architecture and training objectives make LayoutLMv3 a general-purpose pre-trained model. For example, LayoutLMv3 can be fine-tuned for both text-centric tasks, including form understanding, receipt understanding, and document visual question answering, and image-centric tasks such as document image classification and document layout analysis. [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://arxiv.org/abs/2204.08387) Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, Furu Wei, ACM Multimedia 2022. ## Citation If you find LayoutLM useful in your research, please cite the following paper: ``` @inproceedings{huang2022layoutlmv3, author={Yupan Huang and Tengchao Lv and Lei Cui and Yutong Lu and Furu Wei}, title={LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking}, booktitle={Proceedings of the 30th ACM International Conference on Multimedia}, year={2022} } ``` ## License The content of this project itself is licensed under the [Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/). Portions of the source code are based on the [transformers](https://github.com/huggingface/transformers) project. [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct)

amunchet/rorshark-vit-base

amunchet

transformers

image-classification

--- license: apache-2.0 base_model: google/vit-base-patch16-224-in21k tags: - image-classification - vision - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: rorshark-vit-base results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.9922928709055877 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # rorshark-vit-base This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0393 - Accuracy: 0.9923 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 1337 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.0597 | 1.0 | 368 | 0.0546 | 0.9865 | | 0.2009 | 2.0 | 736 | 0.0531 | 0.9865 | | 0.0114 | 3.0 | 1104 | 0.0418 | 0.9904 | | 0.0998 | 4.0 | 1472 | 0.0425 | 0.9904 | | 0.1244 | 5.0 | 1840 | 0.0393 | 0.9923 | ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.1+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0

facebook/dpr-ctx_encoder-single-nq-base

facebook

transformers

--- language: en license: cc-by-nc-4.0 tags: - dpr datasets: - nq_open inference: false --- # `dpr-ctx_encoder-single-nq-base` ## Table of Contents - [Model Details](#model-details) - [How To Get Started With the Model](#how-to-get-started-with-the-model) - [Uses](#uses) - [Risks, Limitations and Biases](#risks-limitations-and-biases) - [Training](#training) - [Evaluation](#evaluation-results) - [Environmental Impact](#environmental-impact) - [Technical Specifications](#technical-specifications) - [Citation Information](#citation-information) - [Model Card Authors](#model-card-authors) ## Model Details **Model Description:** [Dense Passage Retrieval (DPR)](https://github.com/facebookresearch/DPR) is a set of tools and models for state-of-the-art open-domain Q&A research. `dpr-ctx_encoder-single-nq-base` is the Context Encoder trained using the [Natural Questions (NQ) dataset](https://huggingface.co/datasets/nq_open) ([Lee et al., 2019](https://aclanthology.org/P19-1612/); [Kwiatkowski et al., 2019](https://aclanthology.org/Q19-1026/)). - **Developed by:** See [GitHub repo](https://github.com/facebookresearch/DPR) for model developers - **Model Type:** BERT-based encoder - **Language(s):** [CC-BY-NC-4.0](https://github.com/facebookresearch/DPR/blob/main/LICENSE), also see [Code of Conduct](https://github.com/facebookresearch/DPR/blob/main/CODE_OF_CONDUCT.md) - **License:** English - **Related Models:** - [`dpr-question-encoder-single-nq-base`](https://huggingface.co/facebook/dpr-question_encoder-single-nq-base) - [`dpr-reader-single-nq-base`](https://huggingface.co/facebook/dpr-reader-single-nq-base) - [`dpr-ctx_encoder-multiset-base`](https://huggingface.co/facebook/dpr-ctx_encoder-multiset-base) - [`dpr-question_encoder-multiset-base`](https://huggingface.co/facebook/dpr-question_encoder-multiset-base) - [`dpr-reader-multiset-base`](https://huggingface.co/facebook/dpr-reader-multiset-base) - **Resources for more information:** - [Research Paper](https://arxiv.org/abs/2004.04906) - [GitHub Repo](https://github.com/facebookresearch/DPR) - [Hugging Face DPR docs](https://huggingface.co/docs/transformers/main/en/model_doc/dpr) - [BERT Base Uncased Model Card](https://huggingface.co/bert-base-uncased) ## How to Get Started with the Model Use the code below to get started with the model. ```python >>> from transformers import DPRContextEncoder, DPRContextEncoderTokenizer >>> tokenizer = DPRContextEncoderTokenizer.from_pretrained("facebook/dpr-ctx_encoder-single-nq-base") >>> model = DPRContextEncoder.from_pretrained("facebook/dpr-ctx_encoder-single-nq-base") >>> input_ids = tokenizer("Hello, is my dog cute ?", return_tensors="pt")["input_ids"] >>> embeddings = model(input_ids).pooler_output ``` ## Uses #### Direct Use `dpr-ctx_encoder-single-nq-base`, [`dpr-question-encoder-single-nq-base`](https://huggingface.co/facebook/dpr-question_encoder-single-nq-base), and [`dpr-reader-single-nq-base`](https://huggingface.co/facebook/dpr-reader-single-nq-base) can be used for the task of open-domain question answering. #### Misuse and Out-of-scope Use The model should not be used to intentionally create hostile or alienating environments for people. In addition, the set of DPR models was not trained to be factual or true representations of people or events, and therefore using the models to generate such content is out-of-scope for the abilities of this model. ## Risks, Limitations and Biases **CONTENT WARNING: Readers should be aware this section may contain content that is disturbing, offensive, and can propogate historical and current stereotypes.** Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model can include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups. ## Training #### Training Data This model was trained using the [Natural Questions (NQ) dataset](https://huggingface.co/datasets/nq_open) ([Lee et al., 2019](https://aclanthology.org/P19-1612/); [Kwiatkowski et al., 2019](https://aclanthology.org/Q19-1026/)). The model authors write that: > [The dataset] was designed for end-to-end question answering. The questions were mined from real Google search queries and the answers were spans in Wikipedia articles identified by annotators. #### Training Procedure The training procedure is described in the [associated paper](https://arxiv.org/pdf/2004.04906.pdf): > Given a collection of M text passages, the goal of our dense passage retriever (DPR) is to index all the passages in a low-dimensional and continuous space, such that it can retrieve efficiently the top k passages relevant to the input question for the reader at run-time. > Our dense passage retriever (DPR) uses a dense encoder EP(·) which maps any text passage to a d- dimensional real-valued vectors and builds an index for all the M passages that we will use for retrieval. At run-time, DPR applies a different encoder EQ(·) that maps the input question to a d-dimensional vector, and retrieves k passages of which vectors are the closest to the question vector. The authors report that for encoders, they used two independent BERT ([Devlin et al., 2019](https://aclanthology.org/N19-1423/)) networks (base, un-cased) and use FAISS ([Johnson et al., 2017](https://arxiv.org/abs/1702.08734)) during inference time to encode and index passages. See the paper for further details on training, including encoders, inference, positive and negative passages, and in-batch negatives. ## Evaluation The following evaluation information is extracted from the [associated paper](https://arxiv.org/pdf/2004.04906.pdf). #### Testing Data, Factors and Metrics The model developers report the performance of the model on five QA datasets, using the top-k accuracy (k ∈ {20, 100}). The datasets were [NQ](https://huggingface.co/datasets/nq_open), [TriviaQA](https://huggingface.co/datasets/trivia_qa), [WebQuestions (WQ)](https://huggingface.co/datasets/web_questions), [CuratedTREC (TREC)](https://huggingface.co/datasets/trec), and [SQuAD v1.1](https://huggingface.co/datasets/squad). #### Results | | Top 20 | | | | | Top 100| | | | | |:----:|:------:|:---------:|:--:|:----:|:-----:|:------:|:---------:|:--:|:----:|:-----:| | | NQ | TriviaQA | WQ | TREC | SQuAD | NQ | TriviaQA | WQ | TREC | SQuAD | | | 78.4 | 79.4 |73.2| 79.8 | 63.2 | 85.4 | 85.0 |81.4| 89.1 | 77.2 | ## Environmental Impact Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). We present the hardware type and based on the [associated paper](https://arxiv.org/abs/2004.04906). - **Hardware Type:** 8 32GB GPUs - **Hours used:** Unknown - **Cloud Provider:** Unknown - **Compute Region:** Unknown - **Carbon Emitted:** Unknown ## Technical Specifications See the [associated paper](https://arxiv.org/abs/2004.04906) for details on the modeling architecture, objective, compute infrastructure, and training details. ## Citation Information ```bibtex @inproceedings{karpukhin-etal-2020-dense, title = "Dense Passage Retrieval for Open-Domain Question Answering", author = "Karpukhin, Vladimir and Oguz, Barlas and Min, Sewon and Lewis, Patrick and Wu, Ledell and Edunov, Sergey and Chen, Danqi and Yih, Wen-tau", booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/2020.emnlp-main.550", doi = "10.18653/v1/2020.emnlp-main.550", pages = "6769--6781", } ``` ## Model Card Authors This model card was written by the team at Hugging Face.

microsoft/git-base

microsoft

transformers

image-to-text

--- language: en license: mit tags: - vision - image-to-text - image-captioning model_name: microsoft/git-base pipeline_tag: image-to-text --- # GIT (GenerativeImage2Text), base-sized GIT (short for GenerativeImage2Text) model, base-sized version. It was introduced in the paper [GIT: A Generative Image-to-text Transformer for Vision and Language](https://arxiv.org/abs/2205.14100) by Wang et al. and first released in [this repository](https://github.com/microsoft/GenerativeImage2Text). Disclaimer: The team releasing GIT did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description GIT is a Transformer decoder conditioned on both CLIP image tokens and text tokens. The model is trained using "teacher forcing" on a lot of (image, text) pairs. The goal for the model is simply to predict the next text token, giving the image tokens and previous text tokens. The model has full access to (i.e. a bidirectional attention mask is used for) the image patch tokens, but only has access to the previous text tokens (i.e. a causal attention mask is used for the text tokens) when predicting the next text token.  This allows the model to be used for tasks like: - image and video captioning - visual question answering (VQA) on images and videos - even image classification (by simply conditioning the model on the image and asking it to generate a class for it in text). ## Intended uses & limitations You can use the raw model for image captioning. See the [model hub](https://huggingface.co/models?search=microsoft/git) to look for fine-tuned versions on a task that interests you. ### How to use For code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/main/model_doc/git#transformers.GitForCausalLM.forward.example). ## Training data From the paper: > We collect 0.8B image-text pairs for pre-training, which include COCO (Lin et al., 2014), Conceptual Captions (CC3M) (Sharma et al., 2018), SBU (Ordonez et al., 2011), Visual Genome (VG) (Krishna et al., 2016), Conceptual Captions (CC12M) (Changpinyo et al., 2021), ALT200M (Hu et al., 2021a), and an extra 0.6B data following a similar collection procedure in Hu et al. (2021a). => however this is for the model referred to as "GIT" in the paper, which is not open-sourced. This checkpoint is "GIT-base", which is a smaller variant of GIT trained on 10 million image-text pairs. See table 11 in the [paper](https://arxiv.org/abs/2205.14100) for more details. ### Preprocessing We refer to the original repo regarding details for preprocessing during training. During validation, one resizes the shorter edge of each image, after which center cropping is performed to a fixed-size resolution. Next, frames are normalized across the RGB channels with the ImageNet mean and standard deviation. ## Evaluation results For evaluation results, we refer readers to the [paper](https://arxiv.org/abs/2205.14100).

dslim/bert-base-NER-uncased

dslim

transformers

token-classification

--- license: mit ---

facebook/wav2vec2-large-xlsr-53

facebook

transformers

--- language: multilingual datasets: - common_voice tags: - speech license: apache-2.0 --- # Wav2Vec2-XLSR-53 [Facebook's XLSR-Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) The base model pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. Note that this model should be fine-tuned on a downstream task, like Automatic Speech Recognition. Check out [this blog](https://huggingface.co/blog/fine-tune-wav2vec2-english) for more information. [Paper](https://arxiv.org/abs/2006.13979) Authors: Alexis Conneau, Alexei Baevski, Ronan Collobert, Abdelrahman Mohamed, Michael Auli **Abstract** This paper presents XLSR which learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations and jointly learns a quantization of the latents shared across languages. The resulting model is fine-tuned on labeled data and experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining. On the CommonVoice benchmark, XLSR shows a relative phoneme error rate reduction of 72% compared to the best known results. On BABEL, our approach improves word error rate by 16% relative compared to a comparable system. Our approach enables a single multilingual speech recognition model which is competitive to strong individual models. Analysis shows that the latent discrete speech representations are shared across languages with increased sharing for related languages. We hope to catalyze research in low-resource speech understanding by releasing XLSR-53, a large model pretrained in 53 languages. The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20. # Usage See [this notebook](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/Fine_Tune_XLSR_Wav2Vec2_on_Turkish_ASR_with_%F0%9F%A4%97_Transformers.ipynb) for more information on how to fine-tune the model. 

TheBloke/Llama-2-7B-Chat-GGUF

TheBloke

transformers

text-generation

--- language: - en license: llama2 tags: - facebook - meta - pytorch - llama - llama-2 model_name: Llama 2 7B Chat arxiv: 2307.09288 base_model: meta-llama/Llama-2-7b-chat-hf inference: false model_creator: Meta Llama 2 model_type: llama pipeline_tag: text-generation prompt_template: '[INST] <<SYS>> You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don''t know the answer to a question, please don''t share false information. <</SYS>> {prompt}[/INST] ' quantized_by: TheBloke --- <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Llama 2 7B Chat - GGUF - Model creator: [Meta Llama 2](https://huggingface.co/meta-llama) - Original model: [Llama 2 7B Chat](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) <!-- description start --> ## Description This repo contains GGUF format model files for [Meta Llama 2's Llama 2 7B Chat](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf). <!-- description end --> <!-- README_GGUF.md-about-gguf start --> ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible. Here is an incomplate list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. <!-- README_GGUF.md-about-gguf end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Llama-2-7b-Chat-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF) * [Meta Llama 2's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: Llama-2-Chat ``` [INST] <<SYS>> You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information. <</SYS>> {prompt}[/INST] ``` <!-- prompt-template end --> <!-- compatibility_gguf start --> ## Compatibility These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) They are also compatible with many third party UIs and libraries - please see the list at the top of this README. ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how. </details> <!-- compatibility_gguf end --> <!-- README_GGUF.md-provided-files start --> ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [llama-2-7b-chat.Q2_K.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/blob/main/llama-2-7b-chat.Q2_K.gguf) | Q2_K | 2 | 2.83 GB| 5.33 GB | smallest, significant quality loss - not recommended for most purposes | | [llama-2-7b-chat.Q3_K_S.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/blob/main/llama-2-7b-chat.Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| 5.45 GB | very small, high quality loss | | [llama-2-7b-chat.Q3_K_M.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/blob/main/llama-2-7b-chat.Q3_K_M.gguf) | Q3_K_M | 3 | 3.30 GB| 5.80 GB | very small, high quality loss | | [llama-2-7b-chat.Q3_K_L.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/blob/main/llama-2-7b-chat.Q3_K_L.gguf) | Q3_K_L | 3 | 3.60 GB| 6.10 GB | small, substantial quality loss | | [llama-2-7b-chat.Q4_0.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_0.gguf) | Q4_0 | 4 | 3.83 GB| 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [llama-2-7b-chat.Q4_K_S.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| 6.36 GB | small, greater quality loss | | [llama-2-7b-chat.Q4_K_M.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| 6.58 GB | medium, balanced quality - recommended | | [llama-2-7b-chat.Q5_0.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/blob/main/llama-2-7b-chat.Q5_0.gguf) | Q5_0 | 5 | 4.65 GB| 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [llama-2-7b-chat.Q5_K_S.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/blob/main/llama-2-7b-chat.Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| 7.15 GB | large, low quality loss - recommended | | [llama-2-7b-chat.Q5_K_M.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/blob/main/llama-2-7b-chat.Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| 7.28 GB | large, very low quality loss - recommended | | [llama-2-7b-chat.Q6_K.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/blob/main/llama-2-7b-chat.Q6_K.gguf) | Q6_K | 6 | 5.53 GB| 8.03 GB | very large, extremely low quality loss | | [llama-2-7b-chat.Q8_0.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/blob/main/llama-2-7b-chat.Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| 9.66 GB | very large, extremely low quality loss - not recommended | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. <!-- README_GGUF.md-provided-files end --> <!-- README_GGUF.md-how-to-download start --> ## How to download GGUF files **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: - LM Studio - LoLLMS Web UI - Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/Llama-2-7b-Chat-GGUF and below it, a specific filename to download, such as: llama-2-7b-chat.q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub>=0.17.1 ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/Llama-2-7b-Chat-GGUF llama-2-7b-chat.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/Llama-2-7b-Chat-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Llama-2-7b-Chat-GGUF llama-2-7b-chat.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command. </details> <!-- README_GGUF.md-how-to-download end --> <!-- README_GGUF.md-how-to-run start --> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 32 -m llama-2-7b-chat.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n{prompt}[/INST]" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. ### How to load this model from Python using ctransformers #### First install the package ```bash # Base ctransformers with no GPU acceleration pip install ctransformers>=0.2.24 # Or with CUDA GPU acceleration pip install ctransformers[cuda]>=0.2.24 # Or with ROCm GPU acceleration CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers # Or with Metal GPU acceleration for macOS systems CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers ``` #### Simple example code to load one of these GGUF models ```python from ctransformers import AutoModelForCausalLM # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7b-Chat-GGUF", model_file="llama-2-7b-chat.q4_K_M.gguf", model_type="llama", gpu_layers=50) print(llm("AI is going to")) ``` ## How to use with LangChain Here's guides on using llama-cpp-python or ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) <!-- README_GGUF.md-how-to-run end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Aemon Algiz. **Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> <!-- original-model-card start --> # Original model card: Meta Llama 2's Llama 2 7B Chat # **Llama 2** Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom. ## Model Details *Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the [website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and accept our License before requesting access here.* Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM. **Model Developers** Meta **Variations** Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations. **Input** Models input text only. **Output** Models generate text only. **Model Architecture** Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety. ||Training Data|Params|Content Length|GQA|Tokens|LR| |---|---|---|---|---|---|---| |Llama 2|*A new mix of publicly available online data*|7B|4k|&#10007;|2.0T|3.0 x 10^-4| |Llama 2|*A new mix of publicly available online data*|13B|4k|&#10007;|2.0T|3.0 x 10^-4| |Llama 2|*A new mix of publicly available online data*|70B|4k|&#10004;|2.0T|1.5 x 10^-4| *Llama 2 family of models.* Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. Bigger models - 70B -- use Grouped-Query Attention (GQA) for improved inference scalability. **Model Dates** Llama 2 was trained between January 2023 and July 2023. **Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback. **License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) **Research Paper** ["Llama-2: Open Foundation and Fine-tuned Chat Models"](arxiv.org/abs/2307.09288) ## Intended Use **Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks. To get the expected features and performance for the chat versions, a specific formatting needs to be followed, including the `INST` and `<<SYS>>` tags, `BOS` and `EOS` tokens, and the whitespaces and breaklines in between (we recommend calling `strip()` on inputs to avoid double-spaces). See our reference code in github for details: [`chat_completion`](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L212). **Out-of-scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2. ## Hardware and Software **Training Factors** We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute. **Carbon Footprint** Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Meta’s sustainability program. ||Time (GPU hours)|Power Consumption (W)|Carbon Emitted(tCO₂eq)| |---|---|---|---| |Llama 2 7B|184320|400|31.22| |Llama 2 13B|368640|400|62.44| |Llama 2 70B|1720320|400|291.42| |Total|3311616||539.00| **CO₂ emissions during pretraining.** Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others. ## Training Data **Overview** Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data. **Data Freshness** The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023. ## Evaluation Results In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library. |Model|Size|Code|Commonsense Reasoning|World Knowledge|Reading Comprehension|Math|MMLU|BBH|AGI Eval| |---|---|---|---|---|---|---|---|---|---| |Llama 1|7B|14.1|60.8|46.2|58.5|6.95|35.1|30.3|23.9| |Llama 1|13B|18.9|66.1|52.6|62.3|10.9|46.9|37.0|33.9| |Llama 1|33B|26.0|70.0|58.4|67.6|21.4|57.8|39.8|41.7| |Llama 1|65B|30.7|70.7|60.5|68.6|30.8|63.4|43.5|47.6| |Llama 2|7B|16.8|63.9|48.9|61.3|14.6|45.3|32.6|29.3| |Llama 2|13B|24.5|66.9|55.4|65.8|28.7|54.8|39.4|39.1| |Llama 2|70B|**37.5**|**71.9**|**63.6**|**69.4**|**35.2**|**68.9**|**51.2**|**54.2**| **Overall performance on grouped academic benchmarks.** *Code:* We report the average pass@1 scores of our models on HumanEval and MBPP. *Commonsense Reasoning:* We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. *World Knowledge:* We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. *Reading Comprehension:* For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. *MATH:* We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1. |||TruthfulQA|Toxigen| |---|---|---|---| |Llama 1|7B|27.42|23.00| |Llama 1|13B|41.74|23.08| |Llama 1|33B|44.19|22.57| |Llama 1|65B|48.71|21.77| |Llama 2|7B|33.29|**21.25**| |Llama 2|13B|41.86|26.10| |Llama 2|70B|**50.18**|24.60| **Evaluation of pretrained LLMs on automatic safety benchmarks.** For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better). |||TruthfulQA|Toxigen| |---|---|---|---| |Llama-2-Chat|7B|57.04|**0.00**| |Llama-2-Chat|13B|62.18|**0.00**| |Llama-2-Chat|70B|**64.14**|0.01| **Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above. ## Ethical Considerations and Limitations Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model. Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide) ## Reporting Issues Please report any software “bug,” or other problems with the models through one of the following means: - Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama) - Reporting problematic content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback) - Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info) ## Llama Model Index |Model|Llama2|Llama2-hf|Llama2-chat|Llama2-chat-hf| |---|---|---|---|---| |7B| [Link](https://huggingface.co/llamaste/Llama-2-7b) | [Link](https://huggingface.co/llamaste/Llama-2-7b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat-hf)| |13B| [Link](https://huggingface.co/llamaste/Llama-2-13b) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-13b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf)| |70B| [Link](https://huggingface.co/llamaste/Llama-2-70b) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-70b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf)| <!-- original-model-card end -->

jonatasgrosman/wav2vec2-large-xlsr-53-polish

jonatasgrosman

transformers

automatic-speech-recognition

--- language: pl license: apache-2.0 datasets: - common_voice - mozilla-foundation/common_voice_6_0 metrics: - wer - cer tags: - audio - automatic-speech-recognition - hf-asr-leaderboard - mozilla-foundation/common_voice_6_0 - pl - robust-speech-event - speech - xlsr-fine-tuning-week model-index: - name: XLSR Wav2Vec2 Polish by Jonatas Grosman results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Common Voice pl type: common_voice args: pl metrics: - name: Test WER type: wer value: 14.21 - name: Test CER type: cer value: 3.49 - name: Test WER (+LM) type: wer value: 10.98 - name: Test CER (+LM) type: cer value: 2.93 - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Robust Speech Event - Dev Data type: speech-recognition-community-v2/dev_data args: pl metrics: - name: Dev WER type: wer value: 33.18 - name: Dev CER type: cer value: 15.92 - name: Dev WER (+LM) type: wer value: 29.31 - name: Dev CER (+LM) type: cer value: 15.17 --- # Fine-tuned XLSR-53 large model for speech recognition in Polish Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Polish using the train and validation splits of [Common Voice 6.1](https://huggingface.co/datasets/common_voice). When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the [OVHcloud](https://www.ovhcloud.com/en/public-cloud/ai-training/) :) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint ## Usage The model can be used directly (without a language model) as follows... Using the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) library: ```python from huggingsound import SpeechRecognitionModel model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-polish") audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"] transcriptions = model.transcribe(audio_paths) ``` Writing your own inference script: ```python import torch import librosa from datasets import load_dataset from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor LANG_ID = "pl" MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-polish" SAMPLES = 5 test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]") processor = Wav2Vec2Processor.from_pretrained(MODEL_ID) model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID) # Preprocessing the datasets. # We need to read the audio files as arrays def speech_file_to_array_fn(batch): speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000) batch["speech"] = speech_array batch["sentence"] = batch["sentence"].upper() return batch test_dataset = test_dataset.map(speech_file_to_array_fn) inputs = processor(test_dataset["speech"], sampling_rate=16_000, return_tensors="pt", padding=True) with torch.no_grad(): logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits predicted_ids = torch.argmax(logits, dim=-1) predicted_sentences = processor.batch_decode(predicted_ids) for i, predicted_sentence in enumerate(predicted_sentences): print("-" * 100) print("Reference:", test_dataset[i]["sentence"]) print("Prediction:", predicted_sentence) ``` | Reference | Prediction | | ------------- | ------------- | | """CZY DRZWI BYŁY ZAMKNIĘTE?""" | PRZY DRZWI BYŁY ZAMKNIĘTE | | GDZIEŻ TU POWÓD DO WYRZUTÓW? | WGDZIEŻ TO POM DO WYRYDÓ | | """O TEM JEDNAK NIE BYŁO MOWY.""" | O TEM JEDNAK NIE BYŁO MOWY | | LUBIĘ GO. | LUBIĄ GO | | — TO MI NIE POMAGA. | TO MNIE NIE POMAGA | | WCIĄŻ LUDZIE WYSIADAJĄ PRZED ZAMKIEM, Z MIASTA, Z PRAGI. | WCIĄŻ LUDZIE WYSIADAJĄ PRZED ZAMKIEM Z MIASTA Z PRAGI | | ALE ON WCALE INACZEJ NIE MYŚLAŁ. | ONY MONITCENIE PONACZUŁA NA MASU | | A WY, CO TAK STOICIE? | A WY CO TAK STOICIE | | A TEN PRZYRZĄD DO CZEGO SŁUŻY? | A TEN PRZYRZĄD DO CZEGO SŁUŻY | | NA JUTRZEJSZYM KOLOKWIUM BĘDZIE PIĘĆ PYTAŃ OTWARTYCH I TEST WIELOKROTNEGO WYBORU. | NAJUTRZEJSZYM KOLOKWIUM BĘDZIE PIĘĆ PYTAŃ OTWARTYCH I TEST WIELOKROTNEGO WYBORU | ## Evaluation 1. To evaluate on `mozilla-foundation/common_voice_6_0` with split `test` ```bash python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-polish --dataset mozilla-foundation/common_voice_6_0 --config pl --split test ``` 2. To evaluate on `speech-recognition-community-v2/dev_data` ```bash python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-polish --dataset speech-recognition-community-v2/dev_data --config pl --split validation --chunk_length_s 5.0 --stride_length_s 1.0 ``` ## Citation If you want to cite this model you can use this: ```bibtex @misc{grosman2021xlsr53-large-polish, title={Fine-tuned {XLSR}-53 large model for speech recognition in {P}olish}, author={Grosman, Jonatas}, howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-polish}}, year={2021} } ```

google/bert_uncased_L-2_H-128_A-2

google

transformers

--- thumbnail: https://huggingface.co/front/thumbnails/google.png license: apache-2.0 --- BERT Miniatures === This is the set of 24 BERT models referenced in [Well-Read Students Learn Better: On the Importance of Pre-training Compact Models](https://arxiv.org/abs/1908.08962) (English only, uncased, trained with WordPiece masking). We have shown that the standard BERT recipe (including model architecture and training objective) is effective on a wide range of model sizes, beyond BERT-Base and BERT-Large. The smaller BERT models are intended for environments with restricted computational resources. They can be fine-tuned in the same manner as the original BERT models. However, they are most effective in the context of knowledge distillation, where the fine-tuning labels are produced by a larger and more accurate teacher. Our goal is to enable research in institutions with fewer computational resources and encourage the community to seek directions of innovation alternative to increasing model capacity. You can download the 24 BERT miniatures either from the [official BERT Github page](https://github.com/google-research/bert/), or via HuggingFace from the links below: | |H=128|H=256|H=512|H=768| |---|:---:|:---:|:---:|:---:| | **L=2** |[**2/128 (BERT-Tiny)**][2_128]|[2/256][2_256]|[2/512][2_512]|[2/768][2_768]| | **L=4** |[4/128][4_128]|[**4/256 (BERT-Mini)**][4_256]|[**4/512 (BERT-Small)**][4_512]|[4/768][4_768]| | **L=6** |[6/128][6_128]|[6/256][6_256]|[6/512][6_512]|[6/768][6_768]| | **L=8** |[8/128][8_128]|[8/256][8_256]|[**8/512 (BERT-Medium)**][8_512]|[8/768][8_768]| | **L=10** |[10/128][10_128]|[10/256][10_256]|[10/512][10_512]|[10/768][10_768]| | **L=12** |[12/128][12_128]|[12/256][12_256]|[12/512][12_512]|[**12/768 (BERT-Base)**][12_768]| Note that the BERT-Base model in this release is included for completeness only; it was re-trained under the same regime as the original model. Here are the corresponding GLUE scores on the test set: |Model|Score|CoLA|SST-2|MRPC|STS-B|QQP|MNLI-m|MNLI-mm|QNLI(v2)|RTE|WNLI|AX| |---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:| |BERT-Tiny|64.2|0.0|83.2|81.1/71.1|74.3/73.6|62.2/83.4|70.2|70.3|81.5|57.2|62.3|21.0| |BERT-Mini|65.8|0.0|85.9|81.1/71.8|75.4/73.3|66.4/86.2|74.8|74.3|84.1|57.9|62.3|26.1| |BERT-Small|71.2|27.8|89.7|83.4/76.2|78.8/77.0|68.1/87.0|77.6|77.0|86.4|61.8|62.3|28.6| |BERT-Medium|73.5|38.0|89.6|86.6/81.6|80.4/78.4|69.6/87.9|80.0|79.1|87.7|62.2|62.3|30.5| For each task, we selected the best fine-tuning hyperparameters from the lists below, and trained for 4 epochs: - batch sizes: 8, 16, 32, 64, 128 - learning rates: 3e-4, 1e-4, 5e-5, 3e-5 If you use these models, please cite the following paper: ``` @article{turc2019, title={Well-Read Students Learn Better: On the Importance of Pre-training Compact Models}, author={Turc, Iulia and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina}, journal={arXiv preprint arXiv:1908.08962v2 }, year={2019} } ``` [2_128]: https://huggingface.co/google/bert_uncased_L-2_H-128_A-2 [2_256]: https://huggingface.co/google/bert_uncased_L-2_H-256_A-4 [2_512]: https://huggingface.co/google/bert_uncased_L-2_H-512_A-8 [2_768]: https://huggingface.co/google/bert_uncased_L-2_H-768_A-12 [4_128]: https://huggingface.co/google/bert_uncased_L-4_H-128_A-2 [4_256]: https://huggingface.co/google/bert_uncased_L-4_H-256_A-4 [4_512]: https://huggingface.co/google/bert_uncased_L-4_H-512_A-8 [4_768]: https://huggingface.co/google/bert_uncased_L-4_H-768_A-12 [6_128]: https://huggingface.co/google/bert_uncased_L-6_H-128_A-2 [6_256]: https://huggingface.co/google/bert_uncased_L-6_H-256_A-4 [6_512]: https://huggingface.co/google/bert_uncased_L-6_H-512_A-8 [6_768]: https://huggingface.co/google/bert_uncased_L-6_H-768_A-12 [8_128]: https://huggingface.co/google/bert_uncased_L-8_H-128_A-2 [8_256]: https://huggingface.co/google/bert_uncased_L-8_H-256_A-4 [8_512]: https://huggingface.co/google/bert_uncased_L-8_H-512_A-8 [8_768]: https://huggingface.co/google/bert_uncased_L-8_H-768_A-12 [10_128]: https://huggingface.co/google/bert_uncased_L-10_H-128_A-2 [10_256]: https://huggingface.co/google/bert_uncased_L-10_H-256_A-4 [10_512]: https://huggingface.co/google/bert_uncased_L-10_H-512_A-8 [10_768]: https://huggingface.co/google/bert_uncased_L-10_H-768_A-12 [12_128]: https://huggingface.co/google/bert_uncased_L-12_H-128_A-2 [12_256]: https://huggingface.co/google/bert_uncased_L-12_H-256_A-4 [12_512]: https://huggingface.co/google/bert_uncased_L-12_H-512_A-8 [12_768]: https://huggingface.co/google/bert_uncased_L-12_H-768_A-12

flair/pos-english

flair

flair

token-classification

--- tags: - flair - token-classification - sequence-tagger-model language: en datasets: - ontonotes inference: false --- ## English Part-of-Speech Tagging in Flair (default model) This is the standard part-of-speech tagging model for English that ships with [Flair](https://github.com/flairNLP/flair/). F1-Score: **98,19** (Ontonotes) Predicts fine-grained POS tags: | **tag** | **meaning** | |---------------------------------|-----------| |ADD | Email | |AFX | Affix | |CC | Coordinating conjunction | |CD | Cardinal number | |DT | Determiner | |EX | Existential there | |FW | Foreign word | |HYPH | Hyphen | |IN | Preposition or subordinating conjunction | |JJ | Adjective | |JJR |Adjective, comparative | |JJS | Adjective, superlative | |LS | List item marker | |MD | Modal | |NFP | Superfluous punctuation | |NN | Noun, singular or mass | |NNP |Proper noun, singular | |NNPS | Proper noun, plural | |NNS |Noun, plural | |PDT | Predeterminer | |POS | Possessive ending | |PRP | Personal pronoun | |PRP$ | Possessive pronoun | |RB | Adverb | |RBR | Adverb, comparative | |RBS | Adverb, superlative | |RP | Particle | |SYM | Symbol | |TO | to | |UH | Interjection | |VB | Verb, base form | |VBD | Verb, past tense | |VBG | Verb, gerund or present participle | |VBN | Verb, past participle | |VBP | Verb, non-3rd person singular present | |VBZ | Verb, 3rd person singular present | |WDT | Wh-determiner | |WP | Wh-pronoun | |WP$ | Possessive wh-pronoun | |WRB | Wh-adverb | |XX | Unknown | Based on [Flair embeddings](https://www.aclweb.org/anthology/C18-1139/) and LSTM-CRF. --- ### Demo: How to use in Flair Requires: **[Flair](https://github.com/flairNLP/flair/)** (`pip install flair`) ```python from flair.data import Sentence from flair.models import SequenceTagger # load tagger tagger = SequenceTagger.load("flair/pos-english") # make example sentence sentence = Sentence("I love Berlin.") # predict NER tags tagger.predict(sentence) # print sentence print(sentence) # print predicted NER spans print('The following NER tags are found:') # iterate over entities and print for entity in sentence.get_spans('pos'): print(entity) ``` This yields the following output: ``` Span [1]: "I" [− Labels: PRP (1.0)] Span [2]: "love" [− Labels: VBP (1.0)] Span [3]: "Berlin" [− Labels: NNP (0.9999)] Span [4]: "." [− Labels: . (1.0)] ``` So, the word "*I*" is labeled as a **pronoun** (PRP), "*love*" is labeled as a **verb** (VBP) and "*Berlin*" is labeled as a **proper noun** (NNP) in the sentence "*I love Berlin*". --- ### Training: Script to train this model The following Flair script was used to train this model: ```python from flair.data import Corpus from flair.datasets import ColumnCorpus from flair.embeddings import WordEmbeddings, StackedEmbeddings, FlairEmbeddings # 1. load the corpus (Ontonotes does not ship with Flair, you need to download and reformat into a column format yourself) corpus: Corpus = ColumnCorpus( "resources/tasks/onto-ner", column_format={0: "text", 1: "pos", 2: "upos", 3: "ner"}, tag_to_bioes="ner", ) # 2. what tag do we want to predict? tag_type = 'pos' # 3. make the tag dictionary from the corpus tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type) # 4. initialize each embedding we use embedding_types = [ # contextual string embeddings, forward FlairEmbeddings('news-forward'), # contextual string embeddings, backward FlairEmbeddings('news-backward'), ] # embedding stack consists of Flair and GloVe embeddings embeddings = StackedEmbeddings(embeddings=embedding_types) # 5. initialize sequence tagger from flair.models import SequenceTagger tagger = SequenceTagger(hidden_size=256, embeddings=embeddings, tag_dictionary=tag_dictionary, tag_type=tag_type) # 6. initialize trainer from flair.trainers import ModelTrainer trainer = ModelTrainer(tagger, corpus) # 7. run training trainer.train('resources/taggers/pos-english', train_with_dev=True, max_epochs=150) ``` --- ### Cite Please cite the following paper when using this model. ``` @inproceedings{akbik2018coling, title={Contextual String Embeddings for Sequence Labeling}, author={Akbik, Alan and Blythe, Duncan and Vollgraf, Roland}, booktitle = {{COLING} 2018, 27th International Conference on Computational Linguistics}, pages = {1638--1649}, year = {2018} } ``` --- ### Issues? The Flair issue tracker is available [here](https://github.com/flairNLP/flair/issues/).

mr8488/distilroberta-finetuned-financial-news-sentiment-analysis

mr8488

transformers

text-classification

--- license: apache-2.0 thumbnail: https://huggingface.co/mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis/resolve/main/logo_no_bg.png tags: - generated_from_trainer - financial - stocks - sentiment widget: - text: "Operating profit totaled EUR 9.4 mn , down from EUR 11.7 mn in 2004 ." - text: "Dunder mifflin Operating profit totaled EUR 9.4 mn , down from EUR 11.7 mn in 2004 ." datasets: - financial_phrasebank metrics: - accuracy model-index: - name: distilRoberta-financial-sentiment results: - task: name: Text Classification type: text-classification dataset: name: financial_phrasebank type: financial_phrasebank args: sentences_allagree metrics: - name: Accuracy type: accuracy value: 0.9923008849557522 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> <div style="text-align:center;width:250px;height:250px;"> <img src="https://huggingface.co/mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis/resolve/main/logo_no_bg.png" alt="logo"> </div> # DistilRoberta-financial-sentiment This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the financial_phrasebank dataset. It achieves the following results on the evaluation set: - Loss: 0.1116 - Accuracy: **0.99**23 ## Base Model description This model is a distilled version of the [RoBERTa-base model](https://huggingface.co/roberta-base). It follows the same training procedure as [DistilBERT](https://huggingface.co/distilbert-base-uncased). The code for the distillation process can be found [here](https://github.com/huggingface/transformers/tree/master/examples/distillation). This model is case-sensitive: it makes a difference between English and English. The model has 6 layers, 768 dimension and 12 heads, totalizing 82M parameters (compared to 125M parameters for RoBERTa-base). On average DistilRoBERTa is twice as fast as Roberta-base. ## Training Data Polar sentiment dataset of sentences from financial news. The dataset consists of 4840 sentences from English language financial news categorised by sentiment. The dataset is divided by agreement rate of 5-8 annotators. ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 255 | 0.1670 | 0.9646 | | 0.209 | 2.0 | 510 | 0.2290 | 0.9558 | | 0.209 | 3.0 | 765 | 0.2044 | 0.9558 | | 0.0326 | 4.0 | 1020 | 0.1116 | 0.9823 | | 0.0326 | 5.0 | 1275 | 0.1127 | 0.9779 | ### Framework versions - Transformers 4.10.2 - Pytorch 1.9.0+cu102 - Datasets 1.12.1 - Tokenizers 0.10.3

timm/resnet18.a1_in1k

timm

timm

image-classification

--- tags: - image-classification - timm license: apache-2.0 library_name: timm --- # Model card for resnet18.a1_in1k A ResNet-B image classification model. This model features: * ReLU activations * single layer 7x7 convolution with pooling * 1x1 convolution shortcut downsample Trained on ImageNet-1k in `timm` using recipe template described below. Recipe details: * ResNet Strikes Back `A1` recipe * LAMB optimizer with BCE loss * Cosine LR schedule with warmup ## Model Details - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 11.7 - GMACs: 1.8 - Activations (M): 2.5 - Image size: train = 224 x 224, test = 288 x 288 - **Papers:** - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 - **Original:** https://github.com/huggingface/pytorch-image-models ## Model Usage ### Image Classification ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model('resnet18.a1_in1k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5) ``` ### Feature Map Extraction ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'resnet18.a1_in1k', pretrained=True, features_only=True, ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 for o in output: # print shape of each feature map in output # e.g.: # torch.Size([1, 64, 112, 112]) # torch.Size([1, 64, 56, 56]) # torch.Size([1, 128, 28, 28]) # torch.Size([1, 256, 14, 14]) # torch.Size([1, 512, 7, 7]) print(o.shape) ``` ### Image Embeddings ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'resnet18.a1_in1k', pretrained=True, num_classes=0, # remove classifier nn.Linear ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 512, 7, 7) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor ``` ## Model Comparison Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results). |model |img_size|top1 |top5 |param_count|gmacs|macts|img/sec| |------------------------------------------|--------|-----|-----|-----------|-----|-----|-------| |[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|320 |86.72|98.17|93.6 |35.2 |69.7 |451 | |[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|288 |86.51|98.08|93.6 |28.5 |56.4 |560 | |[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|288 |86.49|98.03|93.6 |28.5 |56.4 |557 | |[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|224 |85.96|97.82|93.6 |17.2 |34.2 |923 | |[resnext101_32x32d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k)|224 |85.11|97.44|468.5 |87.3 |91.1 |254 | |[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|416 |85.0 |97.12|191.9 |108.4|213.8|134 | |[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|352 |84.96|97.22|102.1 |50.2 |101.2|291 | |[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|320 |84.73|97.18|102.1 |41.5 |83.7 |353 | |[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|384 |84.71|96.99|164.0 |77.6 |154.7|183 | |[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|288 |84.57|97.08|93.6 |28.5 |56.4 |557 | |[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|320 |84.45|97.08|93.2 |31.5 |67.8 |446 | |[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|352 |84.43|96.97|129.9 |51.1 |105.5|280 | |[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|288 |84.36|96.92|93.6 |27.6 |53.0 |595 | |[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|320 |84.35|97.04|66.8 |24.1 |47.7 |610 | |[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 | |[resnext101_32x8d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k)|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 | |[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|320 |84.24|96.86|191.9 |64.2 |126.6|228 | |[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|288 |84.19|96.87|93.6 |27.2 |51.6 |613 | |[resnext101_32x16d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k)|224 |84.18|97.19|194.0 |36.3 |51.2 |581 | |[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 | |[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|320 |83.97|96.82|64.7 |31.2 |67.3 |518 | |[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|256 |83.87|96.75|93.2 |20.2 |43.4 |692 | |[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|224 |83.86|96.65|93.6 |17.2 |34.2 |923 | |[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|320 |83.72|96.61|86.6 |24.3 |48.1 |617 | |[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|256 |83.69|96.78|66.8 |15.4 |30.6 |943 | |[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|224 |83.68|96.61|93.6 |16.7 |32.0 |986 | |[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|320 |83.67|96.74|60.2 |24.1 |47.7 |706 | |[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|256 |83.59|96.61|129.9 |27.1 |55.8 |526 | |[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 | |[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|224 |83.54|96.83|44.6 |9.1 |17.6 |1864 | |[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|288 |83.46|96.54|60.2 |19.1 |37.3 |904 | |[resnext101_32x16d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k)|224 |83.35|96.85|194.0 |36.3 |51.2 |582 | |[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|256 |83.23|96.53|64.7 |20.0 |43.1 |809 | |[resnext101_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k)|224 |83.22|96.75|44.2 |8.0 |21.2 |1814 | |[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|288 |83.16|96.38|83.5 |25.7 |51.6 |590 | |[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|256 |83.14|96.38|60.2 |15.4 |30.5 |1096 | |[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|320 |83.02|96.45|44.6 |16.5 |34.8 |992 | |[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|288 |82.98|96.54|44.6 |13.4 |28.2 |1077 | |[resnext101_64x4d.tv_in1k](https://huggingface.co/timm/resnext101_64x4d.tv_in1k)|224 |82.98|96.25|83.5 |15.5 |31.2 |989 | |[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|256 |82.86|96.28|86.6 |15.6 |30.8 |951 | |[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|224 |82.83|96.22|88.8 |16.5 |31.2 |1099 | |[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|224 |82.8 |96.13|60.2 |11.6 |22.6 |1486 | |[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|288 |82.8 |96.32|44.6 |13.0 |26.8 |1291 | |[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|288 |82.74|95.71|60.2 |19.1 |37.3 |905 | |[resnext101_32x8d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k)|224 |82.69|96.63|88.8 |16.5 |31.2 |1100 | |[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|288 |82.62|95.75|60.2 |19.1 |37.3 |904 | |[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|288 |82.61|96.49|25.6 |8.9 |20.6 |1729 | |[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|288 |82.53|96.13|36.8 |9.9 |21.5 |1773 | |[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|224 |82.5 |96.02|126.9 |22.8 |21.2 |1078 | |[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|224 |82.46|95.92|83.5 |15.5 |31.2 |987 | |[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|288 |82.36|96.18|35.7 |8.1 |20.9 |1964 | |[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|320 |82.35|96.14|25.6 |8.8 |24.1 |1386 | |[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|288 |82.31|95.63|44.6 |13.0 |26.8 |1291 | |[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|288 |82.29|96.01|63.6 |13.6 |28.5 |1078 | |[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|224 |82.29|96.0 |60.2 |11.6 |22.6 |1484 | |[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|288 |82.27|96.06|68.9 |18.9 |23.8 |1176 | |[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|256 |82.26|96.07|44.6 |10.6 |22.2 |1542 | |[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|288 |82.24|95.73|44.6 |13.0 |26.8 |1290 | |[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|288 |82.2 |96.14|27.6 |7.0 |23.8 |1547 | |[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|224 |82.18|96.05|44.6 |8.1 |17.1 |1771 | |[resnext50_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k)|224 |82.17|96.22|25.0 |4.3 |14.4 |2943 | |[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|288 |82.12|95.65|25.6 |7.1 |19.6 |1704 | |[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|288 |82.03|95.94|25.0 |7.0 |23.8 |1745 | |[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|288 |82.0 |96.15|24.9 |5.8 |12.7 |1787 | |[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|256 |81.99|95.85|36.8 |7.8 |17.0 |2230 | |[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|176 |81.98|95.72|88.8 |10.3 |19.4 |1768 | |[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|224 |81.97|95.24|60.2 |11.6 |22.6 |1486 | |[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|224 |81.93|95.75|44.6 |7.8 |16.2 |2122 | |[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|224 |81.9 |95.77|44.6 |7.8 |16.2 |2118 | |[resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k)|224 |81.84|96.1 |194.0 |36.3 |51.2 |583 | |[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|256 |81.78|95.94|35.7 |6.4 |16.6 |2471 | |[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|224 |81.77|95.22|60.2 |11.6 |22.6 |1485 | |[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|224 |81.74|96.06|25.6 |5.4 |12.4 |2813 | |[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|288 |81.65|95.54|25.6 |7.1 |19.6 |1703 | |[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|288 |81.64|95.88|25.6 |7.2 |19.7 |1694 | |[resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k)|224 |81.62|96.04|88.8 |16.5 |31.2 |1101 | |[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|224 |81.61|95.76|68.9 |11.4 |14.4 |1930 | |[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|288 |81.61|95.83|25.6 |8.5 |19.2 |1868 | |[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|224 |81.5 |95.16|44.6 |7.8 |16.2 |2125 | |[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|288 |81.48|95.16|25.0 |7.0 |23.8 |1745 | |[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|288 |81.47|95.71|25.9 |6.9 |18.6 |2071 | |[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|224 |81.45|95.53|68.9 |11.4 |14.4 |1929 | |[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|288 |81.44|95.22|25.6 |7.2 |19.7 |1908 | |[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|256 |81.44|95.67|25.6 |5.6 |15.4 |2168 | |[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|288 |81.4 |95.82|30.2 |6.8 |13.9 |2132 | |[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|288 |81.37|95.74|25.6 |7.2 |19.7 |1910 | |[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|224 |81.32|95.19|44.6 |7.8 |16.2 |2125 | |[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|288 |81.3 |95.65|28.1 |6.8 |18.4 |1803 | |[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|288 |81.3 |95.11|25.0 |7.0 |23.8 |1746 | |[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|224 |81.27|95.62|27.6 |4.3 |14.4 |2591 | |[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|224 |81.26|95.16|25.6 |4.3 |11.8 |2823 | |[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|288 |81.23|95.54|15.7 |4.8 |19.6 |2117 | |[senet154.gluon_in1k](https://huggingface.co/timm/senet154.gluon_in1k)|224 |81.23|95.35|115.1 |20.8 |38.7 |545 | |[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|288 |81.22|95.11|25.6 |6.8 |18.4 |2089 | |[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|288 |81.22|95.63|25.6 |6.8 |18.4 |676 | |[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|288 |81.18|95.09|25.6 |7.2 |19.7 |1908 | |[resnet50.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k)|224 |81.18|95.98|25.6 |4.1 |11.1 |3455 | |[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|224 |81.17|95.34|25.0 |4.3 |14.4 |2933 | |[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|224 |81.1 |95.33|25.0 |4.3 |14.4 |2934 | |[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|288 |81.1 |95.23|28.1 |6.8 |18.4 |1801 | |[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|288 |81.1 |95.12|28.1 |6.8 |18.4 |1799 | |[resnet152s.gluon_in1k](https://huggingface.co/timm/resnet152s.gluon_in1k)|224 |81.02|95.41|60.3 |12.9 |25.0 |1347 | |[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|288 |80.97|95.44|25.6 |6.8 |18.4 |2085 | |[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|256 |80.94|95.45|25.9 |5.4 |14.7 |2571 | |[resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.93|95.73|44.2 |8.0 |21.2 |1814 | |[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|288 |80.91|95.55|25.6 |6.8 |18.4 |2084 | |[seresnext101_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k)|224 |80.9 |95.31|49.0 |8.0 |21.3 |1585 | |[seresnext101_64x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k)|224 |80.9 |95.3 |88.2 |15.5 |31.2 |918 | |[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|288 |80.86|95.52|25.6 |6.8 |18.4 |2085 | |[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|224 |80.85|95.43|25.6 |4.1 |11.1 |3450 | |[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|224 |80.84|95.02|25.6 |4.3 |11.8 |2821 | |[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|224 |80.79|95.62|24.9 |3.5 |7.7 |2961 | |[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|288 |80.79|95.36|19.8 |6.0 |14.8 |2506 | |[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|288 |80.79|95.58|19.9 |4.2 |10.6 |2349 | |[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|288 |80.78|94.99|25.6 |6.8 |18.4 |2088 | |[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|288 |80.71|95.43|25.6 |6.8 |18.4 |2087 | |[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|288 |80.7 |95.39|25.0 |7.0 |23.8 |1749 | |[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|192 |80.69|95.24|63.6 |6.0 |12.7 |2270 | |[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|224 |80.68|94.71|25.6 |4.4 |11.9 |3162 | |[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|288 |80.68|95.36|19.7 |6.0 |14.8 |2637 | |[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|224 |80.67|95.3 |25.6 |4.1 |11.1 |3452 | |[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|288 |80.67|95.42|25.0 |7.4 |25.1 |1626 | |[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|224 |80.63|95.21|25.6 |5.2 |11.6 |3034 | |[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|224 |80.61|95.32|25.6 |4.4 |11.9 |2813 | |[resnext101_64x4d.gluon_in1k](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k)|224 |80.61|94.99|83.5 |15.5 |31.2 |989 | |[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|288 |80.6 |95.31|19.9 |6.0 |14.8 |2578 | |[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|256 |80.57|95.17|15.7 |3.8 |15.5 |2710 | |[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|224 |80.56|95.0 |60.2 |11.6 |22.6 |1483 | |[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|224 |80.53|95.16|25.6 |4.4 |11.9 |3164 | |[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|224 |80.53|94.46|25.0 |4.3 |14.4 |2930 | |[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|176 |80.48|94.98|126.9 |14.3 |13.2 |1719 | |[resnet152d.gluon_in1k](https://huggingface.co/timm/resnet152d.gluon_in1k)|224 |80.47|95.2 |60.2 |11.8 |23.4 |1428 | |[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|288 |80.45|95.32|25.6 |6.8 |18.4 |2086 | |[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|224 |80.45|95.24|30.2 |4.1 |8.4 |3530 | |[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|224 |80.45|94.63|25.0 |4.3 |14.4 |2936 | |[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|176 |80.43|95.09|68.9 |7.3 |9.0 |3015 | |[resnet101d.gluon_in1k](https://huggingface.co/timm/resnet101d.gluon_in1k)|224 |80.42|95.01|44.6 |8.1 |17.0 |2007 | |[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|224 |80.38|94.6 |25.6 |4.1 |11.1 |3461 | |[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|256 |80.36|95.1 |19.8 |4.8 |11.7 |3267 | |[resnext101_32x4d.gluon_in1k](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k)|224 |80.34|94.93|44.2 |8.0 |21.2 |1814 | |[resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.32|95.4 |25.0 |4.3 |14.4 |2941 | |[resnet101s.gluon_in1k](https://huggingface.co/timm/resnet101s.gluon_in1k)|224 |80.28|95.16|44.7 |9.2 |18.6 |1851 | |[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|224 |80.26|95.08|28.1 |4.1 |11.1 |2972 | |[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|288 |80.24|95.24|25.6 |8.5 |19.9 |1523 | |[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|224 |80.22|94.63|25.6 |4.4 |11.9 |3162 | |[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|176 |80.2 |94.64|60.2 |7.2 |14.0 |2346 | |[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|224 |80.08|94.74|28.1 |4.1 |11.1 |2969 | |[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|256 |80.08|94.97|19.7 |4.8 |11.7 |3284 | |[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|256 |80.06|94.99|19.9 |4.8 |11.7 |3216 | |[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|224 |80.06|94.95|25.6 |4.1 |11.1 |1109 | |[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|224 |80.02|94.71|28.1 |4.1 |11.1 |2962 | |[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|288 |79.97|95.05|25.6 |6.8 |18.4 |2086 | |[resnet152c.gluon_in1k](https://huggingface.co/timm/resnet152c.gluon_in1k)|224 |79.92|94.84|60.2 |11.8 |23.4 |1455 | |[seresnext50_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k)|224 |79.91|94.82|27.6 |4.3 |14.4 |2591 | |[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|224 |79.91|94.67|25.6 |4.1 |11.1 |3456 | |[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|176 |79.9 |94.6 |44.6 |4.9 |10.1 |3341 | |[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|224 |79.89|94.97|35.7 |4.5 |12.1 |2774 | |[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|224 |79.88|94.87|25.6 |4.1 |11.1 |3455 | |[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|320 |79.86|95.07|16.0 |5.2 |16.4 |2168 | |[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|224 |79.85|94.56|25.6 |4.1 |11.1 |3460 | |[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|288 |79.83|94.97|25.6 |6.8 |18.4 |2087 | |[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|224 |79.82|94.62|44.6 |7.8 |16.2 |2114 | |[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|224 |79.76|94.6 |25.0 |4.3 |14.4 |2943 | |[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|224 |79.74|94.95|25.6 |4.1 |11.1 |3455 | |[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|224 |79.74|94.87|19.9 |2.5 |6.4 |3929 | |[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|288 |79.71|94.83|19.7 |6.0 |14.8 |2710 | |[resnet152.gluon_in1k](https://huggingface.co/timm/resnet152.gluon_in1k)|224 |79.68|94.74|60.2 |11.6 |22.6 |1486 | |[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|224 |79.67|94.87|25.0 |4.5 |15.2 |2729 | |[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|288 |79.63|94.91|25.6 |6.8 |18.4 |2086 | |[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|224 |79.56|94.72|25.6 |4.3 |11.8 |2805 | |[resnet101c.gluon_in1k](https://huggingface.co/timm/resnet101c.gluon_in1k)|224 |79.53|94.58|44.6 |8.1 |17.0 |2062 | |[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|224 |79.52|94.61|25.6 |4.1 |11.1 |3459 | |[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|176 |79.42|94.64|25.6 |2.6 |6.9 |5397 | |[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|288 |79.4 |94.66|18.0 |5.9 |14.6 |2752 | |[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|224 |79.38|94.57|25.6 |4.1 |11.1 |3459 | |[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|176 |79.37|94.3 |25.0 |2.7 |9.0 |4577 | |[resnext50_32x4d.gluon_in1k](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k)|224 |79.36|94.43|25.0 |4.3 |14.4 |2942 | |[resnext101_32x8d.tv_in1k](https://huggingface.co/timm/resnext101_32x8d.tv_in1k)|224 |79.31|94.52|88.8 |16.5 |31.2 |1100 | |[resnet101.gluon_in1k](https://huggingface.co/timm/resnet101.gluon_in1k)|224 |79.31|94.53|44.6 |7.8 |16.2 |2125 | |[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|224 |79.31|94.63|25.6 |5.2 |12.0 |2524 | |[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|176 |79.27|94.49|25.6 |2.6 |6.9 |5404 | |[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|224 |79.25|94.31|25.0 |4.3 |14.4 |2931 | |[resnet50.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k)|224 |79.22|94.84|25.6 |4.1 |11.1 |3451 | |[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|256 |79.21|94.56|19.7 |4.8 |11.7 |3392 | |[resnet50d.gluon_in1k](https://huggingface.co/timm/resnet50d.gluon_in1k)|224 |79.07|94.48|25.6 |4.4 |11.9 |3162 | |[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|224 |79.03|94.38|25.6 |4.1 |11.1 |3453 | |[resnet50.am_in1k](https://huggingface.co/timm/resnet50.am_in1k)|224 |79.01|94.39|25.6 |4.1 |11.1 |3461 | |[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|256 |79.01|94.37|18.0 |4.6 |11.6 |3440 | |[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|256 |78.9 |94.54|16.0 |3.4 |10.5 |3421 | |[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|160 |78.89|94.11|60.2 |5.9 |11.5 |2745 | |[wide_resnet101_2.tv_in1k](https://huggingface.co/timm/wide_resnet101_2.tv_in1k)|224 |78.84|94.28|126.9 |22.8 |21.2 |1079 | |[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|288 |78.83|94.24|16.8 |4.5 |16.8 |2251 | |[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|224 |78.81|94.32|25.6 |4.1 |11.1 |3454 | |[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|288 |78.74|94.33|16.8 |4.5 |16.7 |2264 | |[resnet50s.gluon_in1k](https://huggingface.co/timm/resnet50s.gluon_in1k)|224 |78.72|94.23|25.7 |5.5 |13.5 |2796 | |[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|224 |78.71|94.24|25.6 |4.4 |11.9 |3154 | |[wide_resnet50_2.tv_in1k](https://huggingface.co/timm/wide_resnet50_2.tv_in1k)|224 |78.47|94.09|68.9 |11.4 |14.4 |1934 | |[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|224 |78.46|94.27|25.6 |4.1 |11.1 |3454 | |[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|288 |78.43|94.35|21.8 |6.5 |7.5 |3291 | |[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|288 |78.42|94.04|10.5 |3.1 |13.3 |3226 | |[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|320 |78.33|94.13|16.0 |5.2 |16.4 |2391 | |[resnet152.tv_in1k](https://huggingface.co/timm/resnet152.tv_in1k)|224 |78.32|94.04|60.2 |11.6 |22.6 |1487 | |[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|288 |78.28|94.1 |10.4 |3.1 |13.3 |3062 | |[bat_resnext26ts.ch_in1k](https://huggingface.co/timm/bat_resnext26ts.ch_in1k)|256 |78.25|94.1 |10.7 |2.5 |12.5 |3393 | |[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|224 |78.06|93.78|25.6 |4.1 |11.1 |3450 | |[resnet50c.gluon_in1k](https://huggingface.co/timm/resnet50c.gluon_in1k)|224 |78.0 |93.99|25.6 |4.4 |11.9 |3286 | |[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|288 |78.0 |93.91|10.3 |3.1 |13.3 |3297 | |[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|224 |77.98|93.75|16.8 |2.7 |10.1 |3841 | |[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|288 |77.92|93.77|21.8 |6.1 |6.2 |3609 | |[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|160 |77.88|93.71|44.6 |4.0 |8.3 |3926 | |[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|256 |77.87|93.84|16.0 |3.4 |10.5 |3772 | |[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|256 |77.86|93.79|10.4 |2.4 |10.5 |4263 | |[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|160 |77.82|93.81|35.7 |2.3 |6.2 |5238 | |[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|256 |77.81|93.82|10.5 |2.4 |10.5 |4183 | |[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|160 |77.79|93.6 |25.6 |2.2 |6.0 |5329 | |[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|160 |77.73|93.32|25.0 |2.2 |7.4 |5576 | |[resnext50_32x4d.tv_in1k](https://huggingface.co/timm/resnext50_32x4d.tv_in1k)|224 |77.61|93.7 |25.0 |4.3 |14.4 |2944 | |[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|224 |77.59|93.61|16.8 |2.7 |10.2 |3807 | |[resnet50.gluon_in1k](https://huggingface.co/timm/resnet50.gluon_in1k)|224 |77.58|93.72|25.6 |4.1 |11.1 |3455 | |[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|256 |77.44|93.56|10.3 |2.4 |10.5 |4284 | |[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|288 |77.41|93.63|16.0 |4.3 |13.5 |2907 | |[resnet101.tv_in1k](https://huggingface.co/timm/resnet101.tv_in1k)|224 |77.38|93.54|44.6 |7.8 |16.2 |2125 | |[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|160 |77.22|93.27|25.6 |2.2 |6.1 |5982 | |[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|288 |77.17|93.47|10.3 |3.1 |13.3 |3392 | |[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|288 |77.15|93.27|21.8 |6.1 |6.2 |3615 | |[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|224 |77.1 |93.37|21.8 |3.9 |4.5 |5436 | |[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|224 |77.02|93.07|28.1 |4.1 |11.1 |2952 | |[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|256 |76.78|93.13|10.3 |2.4 |10.5 |4410 | |[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|224 |76.7 |93.17|16.0 |2.6 |8.2 |4859 | |[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|288 |76.5 |93.35|21.8 |6.1 |6.2 |3617 | |[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|224 |76.42|92.87|21.8 |3.7 |3.7 |5984 | |[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|288 |76.35|93.18|16.0 |3.9 |12.2 |3331 | |[resnet50.tv_in1k](https://huggingface.co/timm/resnet50.tv_in1k)|224 |76.13|92.86|25.6 |4.1 |11.1 |3457 | |[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|160 |75.96|92.5 |25.6 |2.1 |5.7 |6490 | |[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|224 |75.52|92.44|21.8 |3.7 |3.7 |5991 | |[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|224 |75.3 |92.58|16.0 |2.4 |7.4 |5583 | |[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|224 |75.16|92.18|21.8 |3.7 |3.7 |5994 | |[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|160 |75.1 |92.08|28.1 |2.1 |5.7 |5513 | |[resnet34.gluon_in1k](https://huggingface.co/timm/resnet34.gluon_in1k)|224 |74.57|91.98|21.8 |3.7 |3.7 |5984 | |[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|288 |73.81|91.83|11.7 |3.4 |5.4 |5196 | |[resnet34.tv_in1k](https://huggingface.co/timm/resnet34.tv_in1k)|224 |73.32|91.42|21.8 |3.7 |3.7 |5979 | |[resnet18.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k)|224 |73.28|91.73|11.7 |1.8 |2.5 |10213 | |[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|288 |73.16|91.03|11.7 |3.0 |4.1 |6050 | |[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|224 |72.98|91.11|21.8 |3.7 |3.7 |5967 | |[resnet18.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k)|224 |72.6 |91.42|11.7 |1.8 |2.5 |10213 | |[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|288 |72.37|90.59|11.7 |3.0 |4.1 |6051 | |[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|224 |72.26|90.31|10.1 |1.7 |5.8 |7026 | |[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|224 |72.26|90.68|11.7 |2.1 |3.3 |8707 | |[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|224 |71.49|90.07|11.7 |1.8 |2.5 |10187 | |[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|176 |71.31|89.69|10.1 |1.1 |3.6 |10970 | |[resnet18.gluon_in1k](https://huggingface.co/timm/resnet18.gluon_in1k)|224 |70.84|89.76|11.7 |1.8 |2.5 |10210 | |[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|224 |70.64|89.47|11.7 |1.8 |2.5 |10194 | |[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|160 |70.56|89.52|21.8 |1.9 |1.9 |10737 | |[resnet18.tv_in1k](https://huggingface.co/timm/resnet18.tv_in1k)|224 |69.76|89.07|11.7 |1.8 |2.5 |10205 | |[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|224 |68.34|88.03|5.4 |1.1 |2.4 |13079 | |[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|224 |68.25|88.17|11.7 |1.8 |2.5 |10167 | |[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|176 |66.71|86.96|5.4 |0.7 |1.5 |20327 | |[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|160 |65.66|86.26|11.7 |0.9 |1.3 |18229 | ## Citation ```bibtex @inproceedings{wightman2021resnet, title={ResNet strikes back: An improved training procedure in timm}, author={Wightman, Ross and Touvron, Hugo and Jegou, Herve}, booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future} } ``` ```bibtex @misc{rw2019timm, author = {Ross Wightman}, title = {PyTorch Image Models}, year = {2019}, publisher = {GitHub}, journal = {GitHub repository}, doi = {10.5281/zenodo.4414861}, howpublished = {\url{https://github.com/huggingface/pytorch-image-models}} } ``` ```bibtex @article{He2015, author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun}, title = {Deep Residual Learning for Image Recognition}, journal = {arXiv preprint arXiv:1512.03385}, year = {2015} } ```

facebook/dpr-question_encoder-single-nq-base

facebook

transformers

feature-extraction

--- language: en license: cc-by-nc-4.0 tags: - dpr datasets: - nq_open inference: false --- # `dpr-question_encoder-single-nq-base` ## Table of Contents - [Model Details](#model-details) - [How To Get Started With the Model](#how-to-get-started-with-the-model) - [Uses](#uses) - [Risks, Limitations and Biases](#risks-limitations-and-biases) - [Training](#training) - [Evaluation](#evaluation-results) - [Environmental Impact](#environmental-impact) - [Technical Specifications](#technical-specifications) - [Citation Information](#citation-information) - [Model Card Authors](#model-card-authors) ## Model Details **Model Description:** [Dense Passage Retrieval (DPR)](https://github.com/facebookresearch/DPR) is a set of tools and models for state-of-the-art open-domain Q&A research. `dpr-question_encoder-single-nq-base` is the question encoder trained using the [Natural Questions (NQ) dataset](https://huggingface.co/datasets/nq_open) ([Lee et al., 2019](https://aclanthology.org/P19-1612/); [Kwiatkowski et al., 2019](https://aclanthology.org/Q19-1026/)). - **Developed by:** See [GitHub repo](https://github.com/facebookresearch/DPR) for model developers - **Model Type:** BERT-based encoder - **Language(s):** [CC-BY-NC-4.0](https://github.com/facebookresearch/DPR/blob/main/LICENSE), also see [Code of Conduct](https://github.com/facebookresearch/DPR/blob/main/CODE_OF_CONDUCT.md) - **License:** English - **Related Models:** - [`dpr-ctx_encoder-single-nq-base`](https://huggingface.co/facebook/dpr-ctx_encoder-single-nq-base) - [`dpr-reader-single-nq-base`](https://huggingface.co/facebook/dpr-reader-single-nq-base) - [`dpr-ctx_encoder-multiset-base`](https://huggingface.co/facebook/dpr-ctx_encoder-multiset-base) - [`dpr-question_encoder-multiset-base`](https://huggingface.co/facebook/dpr-question_encoder-multiset-base) - [`dpr-reader-multiset-base`](https://huggingface.co/facebook/dpr-reader-multiset-base) - **Resources for more information:** - [Research Paper](https://arxiv.org/abs/2004.04906) - [GitHub Repo](https://github.com/facebookresearch/DPR) - [Hugging Face DPR docs](https://huggingface.co/docs/transformers/main/en/model_doc/dpr) - [BERT Base Uncased Model Card](https://huggingface.co/bert-base-uncased) ## How to Get Started with the Model Use the code below to get started with the model. ```python from transformers import DPRQuestionEncoder, DPRQuestionEncoderTokenizer tokenizer = DPRQuestionEncoderTokenizer.from_pretrained("facebook/dpr-question_encoder-single-nq-base") model = DPRQuestionEncoder.from_pretrained("facebook/dpr-question_encoder-single-nq-base") input_ids = tokenizer("Hello, is my dog cute ?", return_tensors="pt")["input_ids"] embeddings = model(input_ids).pooler_output ``` ## Uses #### Direct Use `dpr-question_encoder-single-nq-base`, [`dpr-ctx_encoder-single-nq-base`](https://huggingface.co/facebook/dpr-ctx_encoder-single-nq-base), and [`dpr-reader-single-nq-base`](https://huggingface.co/facebook/dpr-reader-single-nq-base) can be used for the task of open-domain question answering. #### Misuse and Out-of-scope Use The model should not be used to intentionally create hostile or alienating environments for people. In addition, the set of DPR models was not trained to be factual or true representations of people or events, and therefore using the models to generate such content is out-of-scope for the abilities of this model. ## Risks, Limitations and Biases **CONTENT WARNING: Readers should be aware this section may contain content that is disturbing, offensive, and can propogate historical and current stereotypes.** Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al., 2021](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al., 2021](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model can include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups. ## Training #### Training Data This model was trained using the [Natural Questions (NQ) dataset](https://huggingface.co/datasets/nq_open) ([Lee et al., 2019](https://aclanthology.org/P19-1612/); [Kwiatkowski et al., 2019](https://aclanthology.org/Q19-1026/)). The model authors write that: > [The dataset] was designed for end-to-end question answering. The questions were mined from real Google search queries and the answers were spans in Wikipedia articles identified by annotators. #### Training Procedure The training procedure is described in the [associated paper](https://arxiv.org/pdf/2004.04906.pdf): > Given a collection of M text passages, the goal of our dense passage retriever (DPR) is to index all the passages in a low-dimensional and continuous space, such that it can retrieve efficiently the top k passages relevant to the input question for the reader at run-time. > Our dense passage retriever (DPR) uses a dense encoder EP(·) which maps any text passage to a d- dimensional real-valued vectors and builds an index for all the M passages that we will use for retrieval. At run-time, DPR applies a different encoder EQ(·) that maps the input question to a d-dimensional vector, and retrieves k passages of which vectors are the closest to the question vector. The authors report that for encoders, they used two independent BERT ([Devlin et al., 2019](https://aclanthology.org/N19-1423/)) networks (base, un-cased) and use FAISS ([Johnson et al., 2017](https://arxiv.org/abs/1702.08734)) during inference time to encode and index passages. See the paper for further details on training, including encoders, inference, positive and negative passages, and in-batch negatives. ## Evaluation The following evaluation information is extracted from the [associated paper](https://arxiv.org/pdf/2004.04906.pdf). #### Testing Data, Factors and Metrics The model developers report the performance of the model on five QA datasets, using the top-k accuracy (k ∈ {20, 100}). The datasets were [NQ](https://huggingface.co/datasets/nq_open), [TriviaQA](https://huggingface.co/datasets/trivia_qa), [WebQuestions (WQ)](https://huggingface.co/datasets/web_questions), [CuratedTREC (TREC)](https://huggingface.co/datasets/trec), and [SQuAD v1.1](https://huggingface.co/datasets/squad). #### Results | | Top 20 | | | | | Top 100| | | | | |:----:|:------:|:---------:|:--:|:----:|:-----:|:------:|:---------:|:--:|:----:|:-----:| | | NQ | TriviaQA | WQ | TREC | SQuAD | NQ | TriviaQA | WQ | TREC | SQuAD | | | 78.4 | 79.4 |73.2| 79.8 | 63.2 | 85.4 | 85.0 |81.4| 89.1 | 77.2 | ## Environmental Impact Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). We present the hardware type and based on the [associated paper](https://arxiv.org/abs/2004.04906). - **Hardware Type:** 8 32GB GPUs - **Hours used:** Unknown - **Cloud Provider:** Unknown - **Compute Region:** Unknown - **Carbon Emitted:** Unknown ## Technical Specifications See the [associated paper](https://arxiv.org/abs/2004.04906) for details on the modeling architecture, objective, compute infrastructure, and training details. ## Citation Information ```bibtex @inproceedings{karpukhin-etal-2020-dense, title = "Dense Passage Retrieval for Open-Domain Question Answering", author = "Karpukhin, Vladimir and Oguz, Barlas and Min, Sewon and Lewis, Patrick and Wu, Ledell and Edunov, Sergey and Chen, Danqi and Yih, Wen-tau", booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/2020.emnlp-main.550", doi = "10.18653/v1/2020.emnlp-main.550", pages = "6769--6781", } ``` ## Model Card Authors This model card was written by the team at Hugging Face.

kredor/punctuate-all

kredor

transformers

token-classification

--- license: mit datasets: - wmt/europarl metrics: - f1 - recall - precision --- This is based on [Oliver Guhr's work](https://huggingface.co/oliverguhr/fullstop-punctuation-multilang-large). The difference is that it is a finetuned xlm-roberta-base instead of an xlm-roberta-large and on twelve languages instead of four. The languages are: English, German, French, Spanish, Bulgarian, Italian, Polish, Dutch, Czech, Portugese, Slovak, Slovenian. ----- report ----- precision recall f1-score support 0 0.99 0.99 0.99 73317475 . 0.94 0.95 0.95 4484845 , 0.86 0.86 0.86 6100650 ? 0.88 0.85 0.86 136479 - 0.60 0.29 0.39 233630 : 0.71 0.49 0.58 152424 accuracy 0.98 84425503 macro avg 0.83 0.74 0.77 84425503 weighted avg 0.98 0.98 0.98 84425503 ----- confusion matrix ----- t/p 0 . , ? - : 0 1.0 0.0 0.0 0.0 0.0 0.0 . 0.0 1.0 0.0 0.0 0.0 0.0 , 0.1 0.0 0.9 0.0 0.0 0.0 ? 0.0 0.1 0.0 0.8 0.0 0.0 - 0.1 0.1 0.5 0.0 0.3 0.0 : 0.0 0.3 0.1 0.0 0.0 0.5

cross-encoder/ms-marco-MiniLM-L-6-v2

cross-encoder

transformers

text-classification

--- license: apache-2.0 --- # Cross-Encoder for MS Marco This model was trained on the [MS Marco Passage Ranking](https://github.com/microsoft/MSMARCO-Passage-Ranking) task. The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See [SBERT.net Retrieve & Re-rank](https://www.sbert.net/examples/applications/retrieve_rerank/README.html) for more details. The training code is available here: [SBERT.net Training MS Marco](https://github.com/UKPLab/sentence-transformers/tree/master/examples/training/ms_marco) ## Usage with Transformers ```python from transformers import AutoTokenizer, AutoModelForSequenceClassification import torch model = AutoModelForSequenceClassification.from_pretrained('model_name') tokenizer = AutoTokenizer.from_pretrained('model_name') features = tokenizer(['How many people live in Berlin?', 'How many people live in Berlin?'], ['Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.', 'New York City is famous for the Metropolitan Museum of Art.'], padding=True, truncation=True, return_tensors="pt") model.eval() with torch.no_grad(): scores = model(**features).logits print(scores) ``` ## Usage with SentenceTransformers The usage becomes easier when you have [SentenceTransformers](https://www.sbert.net/) installed. Then, you can use the pre-trained models like this: ```python from sentence_transformers import CrossEncoder model = CrossEncoder('model_name', max_length=512) scores = model.predict([('Query', 'Paragraph1'), ('Query', 'Paragraph2') , ('Query', 'Paragraph3')]) ``` ## Performance In the following table, we provide various pre-trained Cross-Encoders together with their performance on the [TREC Deep Learning 2019](https://microsoft.github.io/TREC-2019-Deep-Learning/) and the [MS Marco Passage Reranking](https://github.com/microsoft/MSMARCO-Passage-Ranking/) dataset. | Model-Name | NDCG@10 (TREC DL 19) | MRR@10 (MS Marco Dev) | Docs / Sec | | ------------- |:-------------| -----| --- | | **Version 2 models** | | | | cross-encoder/ms-marco-TinyBERT-L-2-v2 | 69.84 | 32.56 | 9000 | cross-encoder/ms-marco-MiniLM-L-2-v2 | 71.01 | 34.85 | 4100 | cross-encoder/ms-marco-MiniLM-L-4-v2 | 73.04 | 37.70 | 2500 | cross-encoder/ms-marco-MiniLM-L-6-v2 | 74.30 | 39.01 | 1800 | cross-encoder/ms-marco-MiniLM-L-12-v2 | 74.31 | 39.02 | 960 | **Version 1 models** | | | | cross-encoder/ms-marco-TinyBERT-L-2 | 67.43 | 30.15 | 9000 | cross-encoder/ms-marco-TinyBERT-L-4 | 68.09 | 34.50 | 2900 | cross-encoder/ms-marco-TinyBERT-L-6 | 69.57 | 36.13 | 680 | cross-encoder/ms-marco-electra-base | 71.99 | 36.41 | 340 | **Other models** | | | | nboost/pt-tinybert-msmarco | 63.63 | 28.80 | 2900 | nboost/pt-bert-base-uncased-msmarco | 70.94 | 34.75 | 340 | nboost/pt-bert-large-msmarco | 73.36 | 36.48 | 100 | Capreolus/electra-base-msmarco | 71.23 | 36.89 | 340 | amberoad/bert-multilingual-passage-reranking-msmarco | 68.40 | 35.54 | 330 | sebastian-hofstaetter/distilbert-cat-margin_mse-T2-msmarco | 72.82 | 37.88 | 720 Note: Runtime was computed on a V100 GPU.

2bytescorp/2b_llama2_7b_mt_ft_ko-en-ko_v0.2

2bytescorp

peft

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.6.0.dev0 - PEFT 0.6.0.dev0

meta-llama/Meta-Llama-3-70B-Instruct

meta-llama

transformers

text-generation

--- language: - en pipeline_tag: text-generation tags: - facebook - meta - pytorch - llama - llama-3 license: llama3 extra_gated_prompt: >- ### META LLAMA 3 COMMUNITY LICENSE AGREEMENT Meta Llama 3 Version Release Date: April 18, 2024 "Agreement" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein. "Documentation" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/. "Licensee" or "you" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf. "Meta Llama 3" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads. "Llama Materials" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement. "Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). 1. License Rights and Redistribution. a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials. b. Redistribution and Use. i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Meta Llama 3” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama 3” at the beginning of any such AI model name. ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you. iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.” iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement. v. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof). 2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights. 3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS. 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING. 5. Intellectual Property. a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama 3” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta. b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications. c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials. 6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement. 7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement. ### Meta Llama 3 Acceptable Use Policy Meta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy) #### Prohibited Uses We want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others’ rights, including to: 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as: 1. Violence or terrorism 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material 3. Human trafficking, exploitation, and sexual violence 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials. 5. Sexual solicitation 6. Any other criminal activity 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system 2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following: 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State 2. Guns and illegal weapons (including weapon development) 3. Illegal drugs and regulated/controlled substances 4. Operation of critical infrastructure, transportation technologies, or heavy machinery 5. Self-harm or harm to others, including suicide, cutting, and eating disorders 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual 3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following: 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content 3. Generating, promoting, or further distributing spam 4. Impersonating another individual without consent, authorization, or legal right 5. Representing that the use of Meta Llama 3 or outputs are human-generated 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 4. Fail to appropriately disclose to end users any known dangers of your AI system Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means: * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3) * Reporting risky content generated by the model: developers.facebook.com/llama_output_feedback * Reporting bugs and security concerns: facebook.com/whitehat/info * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: LlamaUseReport@meta.com extra_gated_fields: First Name: text Last Name: text Date of birth: date_picker Country: country Affiliation: text geo: ip_location By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/). extra_gated_button_content: Submit widget: - example_title: Winter holidays messages: - role: system content: You are a helpful and honest assistant. Please, respond concisely and truthfully. - role: user content: Can you recommend a good destination for Winter holidays? - example_title: Programming assistant messages: - role: system content: You are a helpful and honest code and programming assistant. Please, respond concisely and truthfully. - role: user content: Write a function that computes the nth fibonacci number. inference: parameters: max_new_tokens: 300 stop: - <|end_of_text|> - <|eot_id|> --- ## Model Details Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety. **Model developers** Meta **Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants. **Input** Models input text only. **Output** Models generate text and code only. **Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. <table> <tr> <td> </td> <td><strong>Training Data</strong> </td> <td><strong>Params</strong> </td> <td><strong>Context length</strong> </td> <td><strong>GQA</strong> </td> <td><strong>Token count</strong> </td> <td><strong>Knowledge cutoff</strong> </td> </tr> <tr> <td rowspan="2" >Llama 3 </td> <td rowspan="2" >A new mix of publicly available online data. </td> <td>8B </td> <td>8k </td> <td>Yes </td> <td rowspan="2" >15T+ </td> <td>March, 2023 </td> </tr> <tr> <td>70B </td> <td>8k </td> <td>Yes </td> <td>December, 2023 </td> </tr> </table> **Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability. **Model Release Date** April 18, 2024. **Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback. **License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license) Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes). ## Intended Use **Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks. **Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**. **Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy. ## How to use This repository contains two versions of Meta-Llama-3-70B-Instruct, for use with transformers and with the original `llama3` codebase. ### Use with transformers See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "meta-llama/Meta-Llama-3-70B-Instruct" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto", ) messages = [ {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, {"role": "user", "content": "Who are you?"}, ] terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = pipeline( messages, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.6, top_p=0.9, ) print(outputs[0]["generated_text"][-1]) ``` ### Use with `llama3` Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3). To download Original checkpoints, see the example command below leveraging `huggingface-cli`: ``` huggingface-cli download meta-llama/Meta-Llama-3-70B-Instruct --include "original/*" --local-dir Meta-Llama-3-70B-Instruct ``` For Hugging Face support, we recommend using transformers or TGI, but a similar command works. ## Hardware and Software **Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute. **Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program. <table> <tr> <td> </td> <td><strong>Time (GPU hours)</strong> </td> <td><strong>Power Consumption (W)</strong> </td> <td><strong>Carbon Emitted(tCO2eq)</strong> </td> </tr> <tr> <td>Llama 3 8B </td> <td>1.3M </td> <td>700 </td> <td>390 </td> </tr> <tr> <td>Llama 3 70B </td> <td>6.4M </td> <td>700 </td> <td>1900 </td> </tr> <tr> <td>Total </td> <td>7.7M </td> <td> </td> <td>2290 </td> </tr> </table> **CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others. ## Training Data **Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data. **Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively. ## Benchmarks In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md). ### Base pretrained models <table> <tr> <td><strong>Category</strong> </td> <td><strong>Benchmark</strong> </td> <td><strong>Llama 3 8B</strong> </td> <td><strong>Llama2 7B</strong> </td> <td><strong>Llama2 13B</strong> </td> <td><strong>Llama 3 70B</strong> </td> <td><strong>Llama2 70B</strong> </td> </tr> <tr> <td rowspan="6" >General </td> <td>MMLU (5-shot) </td> <td>66.6 </td> <td>45.7 </td> <td>53.8 </td> <td>79.5 </td> <td>69.7 </td> </tr> <tr> <td>AGIEval English (3-5 shot) </td> <td>45.9 </td> <td>28.8 </td> <td>38.7 </td> <td>63.0 </td> <td>54.8 </td> </tr> <tr> <td>CommonSenseQA (7-shot) </td> <td>72.6 </td> <td>57.6 </td> <td>67.6 </td> <td>83.8 </td> <td>78.7 </td> </tr> <tr> <td>Winogrande (5-shot) </td> <td>76.1 </td> <td>73.3 </td> <td>75.4 </td> <td>83.1 </td> <td>81.8 </td> </tr> <tr> <td>BIG-Bench Hard (3-shot, CoT) </td> <td>61.1 </td> <td>38.1 </td> <td>47.0 </td> <td>81.3 </td> <td>65.7 </td> </tr> <tr> <td>ARC-Challenge (25-shot) </td> <td>78.6 </td> <td>53.7 </td> <td>67.6 </td> <td>93.0 </td> <td>85.3 </td> </tr> <tr> <td>Knowledge reasoning </td> <td>TriviaQA-Wiki (5-shot) </td> <td>78.5 </td> <td>72.1 </td> <td>79.6 </td> <td>89.7 </td> <td>87.5 </td> </tr> <tr> <td rowspan="4" >Reading comprehension </td> <td>SQuAD (1-shot) </td> <td>76.4 </td> <td>72.2 </td> <td>72.1 </td> <td>85.6 </td> <td>82.6 </td> </tr> <tr> <td>QuAC (1-shot, F1) </td> <td>44.4 </td> <td>39.6 </td> <td>44.9 </td> <td>51.1 </td> <td>49.4 </td> </tr> <tr> <td>BoolQ (0-shot) </td> <td>75.7 </td> <td>65.5 </td> <td>66.9 </td> <td>79.0 </td> <td>73.1 </td> </tr> <tr> <td>DROP (3-shot, F1) </td> <td>58.4 </td> <td>37.9 </td> <td>49.8 </td> <td>79.7 </td> <td>70.2 </td> </tr> </table> ### Instruction tuned models <table> <tr> <td><strong>Benchmark</strong> </td> <td><strong>Llama 3 8B</strong> </td> <td><strong>Llama 2 7B</strong> </td> <td><strong>Llama 2 13B</strong> </td> <td><strong>Llama 3 70B</strong> </td> <td><strong>Llama 2 70B</strong> </td> </tr> <tr> <td>MMLU (5-shot) </td> <td>68.4 </td> <td>34.1 </td> <td>47.8 </td> <td>82.0 </td> <td>52.9 </td> </tr> <tr> <td>GPQA (0-shot) </td> <td>34.2 </td> <td>21.7 </td> <td>22.3 </td> <td>39.5 </td> <td>21.0 </td> </tr> <tr> <td>HumanEval (0-shot) </td> <td>62.2 </td> <td>7.9 </td> <td>14.0 </td> <td>81.7 </td> <td>25.6 </td> </tr> <tr> <td>GSM-8K (8-shot, CoT) </td> <td>79.6 </td> <td>25.7 </td> <td>77.4 </td> <td>93.0 </td> <td>57.5 </td> </tr> <tr> <td>MATH (4-shot, CoT) </td> <td>30.0 </td> <td>3.8 </td> <td>6.7 </td> <td>50.4 </td> <td>11.6 </td> </tr> </table> ### Responsibility & Safety We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community. Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications. Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience. As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started. #### Llama 3-Instruct As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case. <span style="text-decoration:underline;">Safety</span> For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable. <span style="text-decoration:underline;">Refusals</span> In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2. We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date. #### Responsible release In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision. Misuse If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/). #### Critical risks <span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives) We have conducted a two fold assessment of the safety of the model in this area: * Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks. * Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model). ### <span style="text-decoration:underline;">Cyber Security </span> We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval). ### <span style="text-decoration:underline;">Child Safety</span> Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences. ### Community Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama). Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community. ## Ethical Considerations and Limitations The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress. But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety. Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide) ## Citation instructions @article{llama3modelcard, title={Llama 3 Model Card}, author={AI@Meta}, year={2024}, url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md} } ## Contributors Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos

sentence-transformers/paraphrase-multilingual-mpnet-base-v2

sentence-transformers

sentence-transformers

sentence-similarity

--- language: - multilingual - ar - bg - ca - cs - da - de - el - en - es - et - fa - fi - fr - gl - gu - he - hi - hr - hu - hy - id - it - ja - ka - ko - ku - lt - lv - mk - mn - mr - ms - my - nb - nl - pl - pt - ro - ru - sk - sl - sq - sr - sv - th - tr - uk - ur - vi license: apache-2.0 library_name: sentence-transformers tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers language_bcp47: - fr-ca - pt-br - zh-cn - zh-tw pipeline_tag: sentence-similarity --- # sentence-transformers/paraphrase-multilingual-mpnet-base-v2 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('sentence-transformers/paraphrase-multilingual-mpnet-base-v2') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-multilingual-mpnet-base-v2') model = AutoModel.from_pretrained('sentence-transformers/paraphrase-multilingual-mpnet-base-v2') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(**encoded_input) # Perform pooling. In this case, average pooling sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/paraphrase-multilingual-mpnet-base-v2) ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False}) ) ``` ## Citing & Authors This model was trained by [sentence-transformers](https://www.sbert.net/). If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084): ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "http://arxiv.org/abs/1908.10084", } ```

oliverguhr/german-sentiment-bert

oliverguhr

transformers

text-classification

--- language: - de tags: - sentiment - bert license: mit widget: - text: "Das ist gar nicht mal so schlecht" metrics: - f1 --- # German Sentiment Classification with Bert This model was trained for sentiment classification of German language texts. To achieve the best results all model inputs needs to be preprocessed with the same procedure, that was applied during the training. To simplify the usage of the model, we provide a Python package that bundles the code need for the preprocessing and inferencing. The model uses the Googles Bert architecture and was trained on 1.834 million German-language samples. The training data contains texts from various domains like Twitter, Facebook and movie, app and hotel reviews. You can find more information about the dataset and the training process in the [paper](http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.202.pdf). ## Using the Python package To get started install the package from [pypi](https://pypi.org/project/germansentiment/): ```bash pip install germansentiment ``` ```python from germansentiment import SentimentModel model = SentimentModel() texts = [ "Mit keinem guten Ergebniss","Das ist gar nicht mal so gut", "Total awesome!","nicht so schlecht wie erwartet", "Der Test verlief positiv.","Sie fährt ein grünes Auto."] result = model.predict_sentiment(texts) print(result) ``` The code above will output following list: ```python ["negative","negative","positive","positive","neutral", "neutral"] ``` ### Output class probabilities ```python from germansentiment import SentimentModel model = SentimentModel() classes, probabilities = model.predict_sentiment(["das ist super"], output_probabilities = True) print(classes, probabilities) ``` ```python ['positive'] [[['positive', 0.9761366844177246], ['negative', 0.023540444672107697], ['neutral', 0.00032294404809363186]]] ``` ## Model and Data If you are interested in code and data that was used to train this model please have a look at [this repository](https://github.com/oliverguhr/german-sentiment) and our [paper](http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.202.pdf). Here is a table of the F1 scores that this model achieves on different datasets. Since we trained this model with a newer version of the transformer library, the results are slightly better than reported in the paper. | Dataset | F1 micro Score | | :----------------------------------------------------------- | -------------: | | [holidaycheck](https://github.com/oliverguhr/german-sentiment) | 0.9568 | | [scare](https://www.romanklinger.de/scare/) | 0.9418 | | [filmstarts](https://github.com/oliverguhr/german-sentiment) | 0.9021 | | [germeval](https://sites.google.com/view/germeval2017-absa/home) | 0.7536 | | [PotTS](https://www.aclweb.org/anthology/L16-1181/) | 0.6780 | | [emotions](https://github.com/oliverguhr/german-sentiment) | 0.9649 | | [sb10k](https://www.spinningbytes.com/resources/germansentiment/) | 0.7376 | | [Leipzig Wikipedia Corpus 2016](https://wortschatz.uni-leipzig.de/de/download/german) | 0.9967 | | all | 0.9639 | ## Cite For feedback and questions contact me view mail or Twitter [@oliverguhr](https://twitter.com/oliverguhr). Please cite us if you found this useful: ``` @InProceedings{guhr-EtAl:2020:LREC, author = {Guhr, Oliver and Schumann, Anne-Kathrin and Bahrmann, Frank and Böhme, Hans Joachim}, title = {Training a Broad-Coverage German Sentiment Classification Model for Dialog Systems}, booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference}, month = {May}, year = {2020}, address = {Marseille, France}, publisher = {European Language Resources Association}, pages = {1620--1625}, url = {https://www.aclweb.org/anthology/2020.lrec-1.202} } ```

TinyPixel/Llama-2-7B-bf16-sharded

TinyPixel

transformers

text-generation

Entry not found

LTP/small

LTP

transformers

   | Language | version | | ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Python](python/interface/README.md) | [](https://pypi.org/project/ltp) [](https://pypi.org/project/ltp-core) [](https://pypi.org/project/ltp-extension) | | [Rust](rust/ltp/README.md) | [](https://crates.io/crates/ltp) | # LTP 4 LTP（Language Technology Platform） 提供了一系列中文自然语言处理工具，用户可以使用这些工具对于中文文本进行分词、词性标注、句法分析等等工作。 ## 引用 如果您在工作中使用了 LTP，您可以引用这篇论文 ```bibtex @article{che2020n, title={N-LTP: A Open-source Neural Chinese Language Technology Platform with Pretrained Models}, author={Che, Wanxiang and Feng, Yunlong and Qin, Libo and Liu, Ting}, journal={arXiv preprint arXiv:2009.11616}, year={2020} } ``` **参考书：** 由哈工大社会计算与信息检索研究中心（HIT-SCIR）的多位学者共同编著的《[自然语言处理：基于预训练模型的方法](https://item.jd.com/13344628.html) 》（作者：车万翔、郭江、崔一鸣；主审：刘挺）一书现已正式出版，该书重点介绍了新的基于预训练模型的自然语言处理技术，包括基础知识、预训练词向量和预训练模型三大部分，可供广大LTP用户学习参考。 ### 更新说明 - 4.2.0 - \[结构性变化\] 将 LTP 拆分成 2 个部分，维护和训练更方便，结构更清晰 - \[Legacy 模型\] 针对广大用户对于**推理速度**的需求，使用 Rust 重写了基于感知机的算法，准确率与 LTP3 版本相当，速度则是 LTP v3 的 **3.55** 倍，开启多线程更可获得 **17.17** 倍的速度提升，但目前仅支持分词、词性、命名实体三大任务 - \[深度学习模型\] 即基于 PyTorch 实现的深度学习模型，支持全部的6大任务（分词/词性/命名实体/语义角色/依存句法/语义依存） - \[其他改进\] 改进了模型训练方法 - \[共同\] 提供了训练脚本和训练样例，使得用户能够更方便地使用私有的数据，自行训练个性化的模型 - \[深度学习模型\] 采用 hydra 对训练过程进行配置，方便广大用户修改模型训练参数以及对 LTP 进行扩展（比如使用其他包中的 Module） - \[其他变化\] 分词、依存句法分析 (Eisner) 和 语义依存分析 (Eisner) 任务的解码算法使用 Rust 实现，速度更快 - \[新特性\] 模型上传至 [Huggingface Hub](https://huggingface.co/LTP)，支持自动下载，下载速度更快，并且支持用户自行上传自己训练的模型供LTP进行推理使用 - \[破坏性变更\] 改用 Pipeline API 进行推理，方便后续进行更深入的性能优化（如SDP和SDPG很大一部分是重叠的，重用可以加快推理速度），使用说明参见[Github快速使用部分](https://github.com/hit-scir/ltp) - 4.1.0 - 提供了自定义分词等功能 - 修复了一些bug - 4.0.0 - 基于Pytorch 开发，原生 Python 接口 - 可根据需要自由选择不同速度和指标的模型 - 分词、词性、命名实体、依存句法、语义角色、语义依存6大任务 ## 快速使用 ### [Python](python/interface/README.md) ```bash pip install -U ltp ltp-core ltp-extension -i https://pypi.org/simple # 安装 ltp ``` **注：** 如果遇到任何错误，请尝试使用上述命令重新安装 ltp，如果依然报错，请在 Github issues 中反馈。 ```python import torch from ltp import LTP ltp = LTP("LTP/small") # 默认加载 Small 模型 # 将模型移动到 GPU 上 if torch.cuda.is_available(): # ltp.cuda() ltp.to("cuda") output = ltp.pipeline(["他叫汤姆去拿外衣。"], tasks=["cws", "pos", "ner", "srl", "dep", "sdp"]) # 使用字典格式作为返回结果 print(output.cws) # print(output[0]) / print(output['cws']) # 也可以使用下标访问 print(output.pos) print(output.sdp) # 使用感知机算法实现的分词、词性和命名实体识别，速度比较快，但是精度略低 ltp = LTP("LTP/legacy") # cws, pos, ner = ltp.pipeline(["他叫汤姆去拿外衣。"], tasks=["cws", "ner"]).to_tuple() # error: NER 需要 词性标注任务的结果 cws, pos, ner = ltp.pipeline(["他叫汤姆去拿外衣。"], tasks=["cws", "pos", "ner"]).to_tuple() # to tuple 可以自动转换为元组格式 # 使用元组格式作为返回结果 print(cws, pos, ner) ``` **[详细说明](python/interface/docs/quickstart.rst)** ### [Rust](rust/ltp/README.md) ```rust use std::fs::File; use itertools::multizip; use ltp::{CWSModel, POSModel, NERModel, ModelSerde, Format, Codec}; fn main() -> Result<(), Box<dyn std::error::Error>> { let file = File::open("data/legacy-models/cws_model.bin")?; let cws: CWSModel = ModelSerde::load(file, Format::AVRO(Codec::Deflate))?; let file = File::open("data/legacy-models/pos_model.bin")?; let pos: POSModel = ModelSerde::load(file, Format::AVRO(Codec::Deflate))?; let file = File::open("data/legacy-models/ner_model.bin")?; let ner: NERModel = ModelSerde::load(file, Format::AVRO(Codec::Deflate))?; let words = cws.predict("他叫汤姆去拿外衣。")?; let pos = pos.predict(&words)?; let ner = ner.predict((&words, &pos))?; for (w, p, n) in multizip((words, pos, ner)) { println!("{}/{}/{}", w, p, n); } Ok(()) } ``` ## 模型性能以及下载地址 | 深度学习模型 | 分词 | 词性 | 命名实体 | 语义角色 | 依存句法 | 语义依存 | 速度(句/S) | | :---------------------------------------: | :---: | :---: | :---: | :---: | :---: | :---: | :-----: | | [Base](https://huggingface.co/LTP/base) | 98.7 | 98.5 | 95.4 | 80.6 | 89.5 | 75.2 | 39.12 | | [Base1](https://huggingface.co/LTP/base1) | 99.22 | 98.73 | 96.39 | 79.28 | 89.57 | 76.57 | --.-- | | [Base2](https://huggingface.co/LTP/base2) | 99.18 | 98.69 | 95.97 | 79.49 | 90.19 | 76.62 | --.-- | | [Small](https://huggingface.co/LTP/small) | 98.4 | 98.2 | 94.3 | 78.4 | 88.3 | 74.7 | 43.13 | | [Tiny](https://huggingface.co/LTP/tiny) | 96.8 | 97.1 | 91.6 | 70.9 | 83.8 | 70.1 | 53.22 | | 感知机算法 | 分词 | 词性 | 命名实体 | 速度(句/s) | 备注 | | :-----------------------------------------: | :---: | :---: | :---: | :------: | :------------------------: | | [Legacy](https://huggingface.co/LTP/legacy) | 97.93 | 98.41 | 94.28 | 21581.48 | [性能详情](rust/ltp/README.md) | **注：感知机算法速度为开启16线程速度** ## 构建 Wheel 包 ```shell script make bdist ``` ## 其他语言绑定 **感知机算法** - [Rust](rust/ltp) - [C/C++](rust/ltp-cffi) **深度学习算法** - [Rust](https://github.com/HIT-SCIR/libltp/tree/master/ltp-rs) - [C++](https://github.com/HIT-SCIR/libltp/tree/master/ltp-cpp) - [Java](https://github.com/HIT-SCIR/libltp/tree/master/ltp-java) ## 作者信息 - 冯云龙 \<\<[ylfeng@ir.hit.edu.cn](mailto:ylfeng@ir.hit.edu.cn)>> ## 开源协议 1. 语言技术平台面向国内外大学、中科院各研究所以及个人研究者免费开放源代码，但如上述机构和个人将该平台用于商业目的（如企业合作项目等）则需要付费。 2. 除上述机构以外的企事业单位，如申请使用该平台，需付费。 3. 凡涉及付费问题，请发邮件到 car@ir.hit.edu.cn 洽商。 4. 如果您在 LTP 基础上发表论文或取得科研成果，请您在发表论文和申报成果时声明“使用了哈工大社会计算与信息检索研究中心研制的语言技术平台（LTP）”. 同时，发信给car@ir.hit.edu.cn，说明发表论文或申报成果的题目、出处等。

google-t5/t5-large

google-t5

transformers

translation

--- language: - en - fr - ro - de - multilingual license: apache-2.0 tags: - summarization - translation datasets: - c4 --- # Model Card for T5 Large  # Table of Contents 1. [Model Details](#model-details) 2. [Uses](#uses) 3. [Bias, Risks, and Limitations](#bias-risks-and-limitations) 4. [Training Details](#training-details) 5. [Evaluation](#evaluation) 6. [Environmental Impact](#environmental-impact) 7. [Citation](#citation) 8. [Model Card Authors](#model-card-authors) 9. [How To Get Started With the Model](#how-to-get-started-with-the-model) # Model Details ## Model Description The developers of the Text-To-Text Transfer Transformer (T5) [write](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html): > With T5, we propose reframing all NLP tasks into a unified text-to-text-format where the input and output are always text strings, in contrast to BERT-style models that can only output either a class label or a span of the input. Our text-to-text framework allows us to use the same model, loss function, and hyperparameters on any NLP task. T5-Large is the checkpoint with 770 million parameters. - **Developed by:** Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu. See [associated paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf) and [GitHub repo](https://github.com/google-research/text-to-text-transfer-transformer#released-model-checkpoints) - **Model type:** Language model - **Language(s) (NLP):** English, French, Romanian, German - **License:** Apache 2.0 - **Related Models:** [All T5 Checkpoints](https://huggingface.co/models?search=t5) - **Resources for more information:** - [Research paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf) - [Google's T5 Blog Post](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) - [GitHub Repo](https://github.com/google-research/text-to-text-transfer-transformer) - [Hugging Face T5 Docs](https://huggingface.co/docs/transformers/model_doc/t5) # Uses ## Direct Use and Downstream Use The developers write in a [blog post](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) that the model: > Our text-to-text framework allows us to use the same model, loss function, and hyperparameters on any NLP task, including machine translation, document summarization, question answering, and classification tasks (e.g., sentiment analysis). We can even apply T5 to regression tasks by training it to predict the string representation of a number instead of the number itself. See the [blog post](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) and [research paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf) for further details. ## Out-of-Scope Use More information needed. # Bias, Risks, and Limitations More information needed. ## Recommendations More information needed. # Training Details ## Training Data The model is pre-trained on the [Colossal Clean Crawled Corpus (C4)](https://www.tensorflow.org/datasets/catalog/c4), which was developed and released in the context of the same [research paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf) as T5. The model was pre-trained on a on a **multi-task mixture of unsupervised (1.) and supervised tasks (2.)**. Thereby, the following datasets were being used for (1.) and (2.): 1. **Datasets used for Unsupervised denoising objective**: - [C4](https://huggingface.co/datasets/c4) - [Wiki-DPR](https://huggingface.co/datasets/wiki_dpr) 2. **Datasets used for Supervised text-to-text language modeling objective** - Sentence acceptability judgment - CoLA [Warstadt et al., 2018](https://arxiv.org/abs/1805.12471) - Sentiment analysis - SST-2 [Socher et al., 2013](https://nlp.stanford.edu/~socherr/EMNLP2013_RNTN.pdf) - Paraphrasing/sentence similarity - MRPC [Dolan and Brockett, 2005](https://aclanthology.org/I05-5002) - STS-B [Ceret al., 2017](https://arxiv.org/abs/1708.00055) - QQP [Iyer et al., 2017](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) - Natural language inference - MNLI [Williams et al., 2017](https://arxiv.org/abs/1704.05426) - QNLI [Rajpurkar et al.,2016](https://arxiv.org/abs/1606.05250) - RTE [Dagan et al., 2005](https://link.springer.com/chapter/10.1007/11736790_9) - CB [De Marneff et al., 2019](https://semanticsarchive.net/Archive/Tg3ZGI2M/Marneffe.pdf) - Sentence completion - COPA [Roemmele et al., 2011](https://www.researchgate.net/publication/221251392_Choice_of_Plausible_Alternatives_An_Evaluation_of_Commonsense_Causal_Reasoning) - Word sense disambiguation - WIC [Pilehvar and Camacho-Collados, 2018](https://arxiv.org/abs/1808.09121) - Question answering - MultiRC [Khashabi et al., 2018](https://aclanthology.org/N18-1023) - ReCoRD [Zhang et al., 2018](https://arxiv.org/abs/1810.12885) - BoolQ [Clark et al., 2019](https://arxiv.org/abs/1905.10044) ## Training Procedure In their [abstract](https://jmlr.org/papers/volume21/20-074/20-074.pdf), the model developers write: > In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts every language problem into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks. The framework introduced, the T5 framework, involves a training procedure that brings together the approaches studied in the paper. See the [research paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf) for further details. # Evaluation ## Testing Data, Factors & Metrics The developers evaluated the model on 24 tasks, see the [research paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf) for full details. ## Results For full results for T5-Large, see the [research paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf), Table 14. # Environmental Impact Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** Google Cloud TPU Pods - **Hours used:** More information needed - **Cloud Provider:** GCP - **Compute Region:** More information needed - **Carbon Emitted:** More information needed # Citation **BibTeX:** ```bibtex @article{2020t5, author = {Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu}, title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer}, journal = {Journal of Machine Learning Research}, year = {2020}, volume = {21}, number = {140}, pages = {1-67}, url = {http://jmlr.org/papers/v21/20-074.html} } ``` **APA:** - Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., ... & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21(140), 1-67. # Model Card Authors This model card was written by the team at Hugging Face. # How to Get Started with the Model Use the code below to get started with the model. <details> <summary> Click to expand </summary> ```python from transformers import T5Tokenizer, T5Model tokenizer = T5Tokenizer.from_pretrained("t5-large") model = T5Model.from_pretrained("t5-large") input_ids = tokenizer( "Studies have been shown that owning a dog is good for you", return_tensors="pt" ).input_ids # Batch size 1 decoder_input_ids = tokenizer("Studies show that", return_tensors="pt").input_ids # Batch size 1 # forward pass outputs = model(input_ids=input_ids, decoder_input_ids=decoder_input_ids) last_hidden_states = outputs.last_hidden_state ``` See the [Hugging Face T5](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5Model) docs and a [Colab Notebook](https://colab.research.google.com/github/google-research/text-to-text-transfer-transformer/blob/main/notebooks/t5-trivia.ipynb) created by the model developers for more examples. </details>

microsoft/trocr-large-stage1

microsoft

transformers

image-to-text

--- tags: - trocr - image-to-text --- # TrOCR (large-sized model, pre-trained only) TrOCR pre-trained only model. It was introduced in the paper [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://arxiv.org/abs/2109.10282) by Li et al. and first released in [this repository](https://github.com/microsoft/unilm/tree/master/trocr). Disclaimer: The team releasing TrOCR did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description The TrOCR model is an encoder-decoder model, consisting of an image Transformer as encoder, and a text Transformer as decoder. The image encoder was initialized from the weights of BEiT, while the text decoder was initialized from the weights of RoBERTa. Images are presented to the model as a sequence of fixed-size patches (resolution 16x16), which are linearly embedded. One also adds absolute position embeddings before feeding the sequence to the layers of the Transformer encoder. Next, the Transformer text decoder autoregressively generates tokens. ## Intended uses & limitations You can use the raw model for optical character recognition (OCR) on single text-line images. See the [model hub](https://huggingface.co/models?search=microsoft/trocr) to look for fine-tuned versions on a task that interests you. ### How to use Here is how to use this model in PyTorch: ```python from transformers import TrOCRProcessor, VisionEncoderDecoderModel from PIL import Image import requests # load image from the IAM database url = 'https://fki.tic.heia-fr.ch/static/img/a01-122-02-00.jpg' image = Image.open(requests.get(url, stream=True).raw).convert("RGB") processor = TrOCRProcessor.from_pretrained('microsoft/trocr-large-stage1') model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-large-stage1') # training pixel_values = processor(image, return_tensors="pt").pixel_values # Batch size 1 decoder_input_ids = torch.tensor([[model.config.decoder.decoder_start_token_id]]) outputs = model(pixel_values=pixel_values, decoder_input_ids=decoder_input_ids) ``` ### BibTeX entry and citation info ```bibtex @misc{li2021trocr, title={TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models}, author={Minghao Li and Tengchao Lv and Lei Cui and Yijuan Lu and Dinei Florencio and Cha Zhang and Zhoujun Li and Furu Wei}, year={2021}, eprint={2109.10282}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

ali-vilab/text-to-video-ms-1.7b

ali-vilab

diffusers

text-to-video

--- license: cc-by-nc-4.0 tags: - text-to-video duplicated_from: diffusers/text-to-video-ms-1.7b --- # Text-to-video-synthesis Model in Open Domain This model is based on a multi-stage text-to-video generation diffusion model, which inputs a description text and returns a video that matches the text description. Only English input is supported. **We Are Hiring!** (Based in Beijing / Hangzhou, China.) If you're looking for an exciting challenge and the opportunity to work with cutting-edge technologies in AIGC and large-scale pretraining, then we are the place for you. We are looking for talented, motivated and creative individuals to join our team. If you are interested, please send your CV to us. EMAIL: yingya.zyy@alibaba-inc.com ## Model description The text-to-video generation diffusion model consists of three sub-networks: text feature extraction model, text feature-to-video latent space diffusion model, and video latent space to video visual space model. The overall model parameters are about 1.7 billion. Currently, it only supports English input. The diffusion model adopts a UNet3D structure, and implements video generation through the iterative denoising process from the pure Gaussian noise video. This model is meant for research purposes. Please look at the [model limitations and biases and misuse](#model-limitations-and-biases), [malicious use and excessive use](#misuse-malicious-use-and-excessive-use) sections. ## Model Details - **Developed by:** [ModelScope](https://modelscope.cn/) - **Model type:** Diffusion-based text-to-video generation model - **Language(s):** English - **License:**[ CC-BY-NC-ND](https://creativecommons.org/licenses/by-nc-nd/4.0/) - **Resources for more information:** [ModelScope GitHub Repository](https://github.com/modelscope/modelscope), [Summary](https://modelscope.cn/models/damo/text-to-video-synthesis/summary). - **Cite as:** ## Use cases This model has a wide range of applications and can reason and generate videos based on arbitrary English text descriptions. ## Usage Let's first install the libraries required: ```bash $ pip install diffusers transformers accelerate torch ``` Now, generate a video: ```python import torch from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler from diffusers.utils import export_to_video pipe = DiffusionPipeline.from_pretrained("damo-vilab/text-to-video-ms-1.7b", torch_dtype=torch.float16, variant="fp16") pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config) pipe.enable_model_cpu_offload() prompt = "Spiderman is surfing" video_frames = pipe(prompt, num_inference_steps=25).frames video_path = export_to_video(video_frames) ``` Here are some results: <table> <tr> <td><center> An astronaut riding a horse. <br> <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astr.gif" alt="An astronaut riding a horse." style="width: 300px;" /> </center></td> <td ><center> Darth vader surfing in waves. <br> <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/vader.gif" alt="Darth vader surfing in waves." style="width: 300px;" /> </center></td> </tr> </table> ## Long Video Generation You can optimize for memory usage by enabling attention and VAE slicing and using Torch 2.0. This should allow you to generate videos up to 25 seconds on less than 16GB of GPU VRAM. ```bash $ pip install git+https://github.com/huggingface/diffusers transformers accelerate ``` ```py import torch from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler from diffusers.utils import export_to_video # load pipeline pipe = DiffusionPipeline.from_pretrained("damo-vilab/text-to-video-ms-1.7b", torch_dtype=torch.float16, variant="fp16") pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config) # optimize for GPU memory pipe.enable_model_cpu_offload() pipe.enable_vae_slicing() # generate prompt = "Spiderman is surfing. Darth Vader is also surfing and following Spiderman" video_frames = pipe(prompt, num_inference_steps=25, num_frames=200).frames # convent to video video_path = export_to_video(video_frames) ``` ## View results The above code will display the save path of the output video, and the current encoding format can be played with [VLC player](https://www.videolan.org/vlc/). The output mp4 file can be viewed by [VLC media player](https://www.videolan.org/vlc/). Some other media players may not view it normally. ## Model limitations and biases * The model is trained based on public data sets such as Webvid, and the generated results may have deviations related to the distribution of training data. * This model cannot achieve perfect film and television quality generation. * The model cannot generate clear text. * The model is mainly trained with English corpus and does not support other languages ​​at the moment**. * The performance of this model needs to be improved on complex compositional generation tasks. ## Misuse, Malicious Use and Excessive Use * The model was not trained to realistically represent people or events, so using it to generate such content is beyond the model's capabilities. * It is prohibited to generate content that is demeaning or harmful to people or their environment, culture, religion, etc. * Prohibited for pornographic, violent and bloody content generation. * Prohibited for error and false information generation. ## Training data The training data includes [LAION5B](https://huggingface.co/datasets/laion/laion2B-en), [ImageNet](https://www.image-net.org/), [Webvid](https://m-bain.github.io/webvid-dataset/) and other public datasets. Image and video filtering is performed after pre-training such as aesthetic score, watermark score, and deduplication. _(Part of this model card has been taken from [here](https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis))_ ## Citation ```bibtex @article{wang2023modelscope, title={Modelscope text-to-video technical report}, author={Wang, Jiuniu and Yuan, Hangjie and Chen, Dayou and Zhang, Yingya and Wang, Xiang and Zhang, Shiwei}, journal={arXiv preprint arXiv:2308.06571}, year={2023} } @InProceedings{VideoFusion, author = {Luo, Zhengxiong and Chen, Dayou and Zhang, Yingya and Huang, Yan and Wang, Liang and Shen, Yujun and Zhao, Deli and Zhou, Jingren and Tan, Tieniu}, title = {VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023} } ```

nvidia/speakerverification_en_titanet_large

nvidia

nemo

--- language: - en library_name: nemo datasets: - VOXCELEB-1 - VOXCELEB-2 - FISHER - switchboard - librispeech_asr - SRE thumbnail: null tags: - speaker - speech - audio - speaker-verification - speaker-recognition - speaker-diarization - titanet - NeMo - pytorch license: cc-by-4.0 widget: - src: https://huggingface.co/nvidia/speakerverification_en_titanet_large/resolve/main/an255-fash-b.wav example_title: Speech sample 1 - src: https://huggingface.co/nvidia/speakerverification_en_titanet_large/resolve/main/cen7-fash-b.wav example_title: Speech sample 2 model-index: - name: speakerverification_en_titanet_large results: - task: name: Speaker Verification type: speaker-verification dataset: name: voxceleb1 type: voxceleb1-O config: clean split: test args: language: en metrics: - name: Test EER type: eer value: 0.66 - task: type: Speaker Diarization name: speaker-diarization dataset: name: ami-mixheadset type: ami_diarization config: oracle-vad-known-number-of-speakers split: test args: language: en metrics: - name: Test DER type: der value: 1.73 - task: type: Speaker Diarization name: speaker-diarization dataset: name: ami-lapel type: ami_diarization config: oracle-vad-known-number-of-speakers split: test args: language: en metrics: - name: Test DER type: der value: 2.03 - task: type: Speaker Diarization name: speaker-diarization dataset: name: ch109 type: callhome_diarization config: oracle-vad-known-number-of-speakers split: test args: language: en metrics: - name: Test DER type: der value: 1.19 - task: type: Speaker Diarization name: speaker-diarization dataset: name: nist-sre-2000 type: nist-sre_diarization config: oracle-vad-known-number-of-speakers split: test args: language: en metrics: - name: Test DER type: der value: 6.73 --- # NVIDIA TitaNet-Large (en-US) <style> img { display: inline; } </style> | [](#model-architecture) | [](#model-architecture) | [](#datasets) This model extracts speaker embeddings from given speech, which is the backbone for speaker verification and diarization tasks. It is a "large" version of TitaNet (around 23M parameters) models. See the [model architecture](#model-architecture) section and [NeMo documentation](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/stable/asr/speaker_recognition/models.html#titanet) for complete architecture details. ## NVIDIA NeMo: Training To train, fine-tune or play with the model you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo). We recommend you install it after you've installed the latest Pytorch version. ``` pip install nemo_toolkit['all'] ``` ## How to Use this Model The model is available for use in the NeMo toolkit [3] and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset. ### Automatically instantiate the model ```python import nemo.collections.asr as nemo_asr speaker_model = nemo_asr.models.EncDecSpeakerLabelModel.from_pretrained("nvidia/speakerverification_en_titanet_large") ``` ### Embedding Extraction Using ```python emb = speaker_model.get_embedding("an255-fash-b.wav") ``` ### Verifying two utterances (Speaker Verification) Now to check if two audio files are from the same speaker or not, simply do: ```python speaker_model.verify_speakers("an255-fash-b.wav","cen7-fash-b.wav") ``` ### Extracting Embeddings for more audio files To extract embeddings from a bunch of audio files: Write audio files to a `manifest.json` file with lines as in format: ```json {"audio_filepath": "<absolute path to dataset>/audio_file.wav", "duration": "duration of file in sec", "label": "speaker_id"} ``` Then running following script will extract embeddings and writes to current working directory: ```shell python <NeMo_root>/examples/speaker_tasks/recognition/extract_speaker_embeddings.py --manifest=manifest.json ``` ### Input This model accepts 16000 KHz Mono-channel Audio (wav files) as input. ### Output This model provides speaker embeddings for an audio file. ## Model Architecture TitaNet model is a depth-wise separable conv1D model [1] for Speaker Verification and diarization tasks. You may find more info on the detail of this model here: [TitaNet-Model](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/speaker_recognition/models.html). ## Training The NeMo toolkit [3] was used for training the models for over several hundred epochs. These model are trained with this [example script](https://github.com/NVIDIA/NeMo/blob/main/examples/speaker_tasks/recognition/speaker_reco.py) and this [base config](https://github.com/NVIDIA/NeMo/blob/main/examples/speaker_tasks/recognition/conf/titanet-large.yaml). ### Datasets All the models in this collection are trained on a composite dataset comprising several thousand hours of English speech: - Voxceleb-1 - Voxceleb-2 - Fisher - Switchboard - Librispeech - SRE (2004-2010) ## Performance Performances of the these models are reported in terms of Equal Error Rate (EER%) on speaker verification evaluation trial files and as Diarization Error Rate (DER%) on diarization test sessions. * Speaker Verification (EER%) | Version | Model | Model Size | VoxCeleb1 (Cleaned trial file) | |---------|--------------|-----|---------------| | 1.10.0 | TitaNet-Large | 23M | 0.66 | * Speaker Diarization (DER%) | Version | Model | Model Size | Evaluation Condition | NIST SRE 2000 | AMI (Lapel) | AMI (MixHeadset) | CH109 | |---------|--------------|-----|----------------------|---------------|-------------|------------------|-------| | 1.10.0 | TitaNet-Large | 23M | Oracle VAD KNOWN # of Speakers | 6.73 | 2.03 | 1.73 | 1.19 | | 1.10.0 | TitaNet-Large | 23M | Oracle VAD UNKNOWN # of Speakers | 5.38 | 2.03 | 1.89 | 1.63 | ## Limitations This model is trained on both telephonic and non-telephonic speech from voxceleb datasets, Fisher and switch board. If your domain of data differs from trained data or doesnot show relatively good performance consider finetuning for that speech domain. ## NVIDIA Riva: Deployment [NVIDIA Riva](https://developer.nvidia.com/riva), is an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, on edge, and embedded. Additionally, Riva provides: * World-class out-of-the-box accuracy for the most common languages with model checkpoints trained on proprietary data with hundreds of thousands of GPU-compute hours * Best in class accuracy with run-time word boosting (e.g., brand and product names) and customization of acoustic model, language model, and inverse text normalization * Streaming speech recognition, Kubernetes compatible scaling, and enterprise-grade support Although this model isn’t supported yet by Riva, the [list of supported models is here](https://huggingface.co/models?other=Riva). Check out [Riva live demo](https://developer.nvidia.com/riva#demos). ## References [1] [TitaNet: Neural Model for Speaker Representation with 1D Depth-wise Separable convolutions and global context](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9746806) [2] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo) ## Licence License to use this model is covered by the [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/). By downloading the public and release version of the model, you accept the terms and conditions of the [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/) license.

EmbeddedLLM/bge-reranker-base-onnx-o3-cpu

EmbeddedLLM

transformers

sentence-similarity

--- pipeline_tag: sentence-similarity tags: - sentence-similarity language: en license: mit --- # ONNX Conversion of [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) - ONNX model for CPU with O3 optimisation ## Usage ```python from itertools import product import torch.nn.functional as F from optimum.onnxruntime import ORTModelForSequenceClassification from transformers import AutoTokenizer sentences = [ "The llama (/ˈlɑːmə/) (Lama glama) is a domesticated South American camelid.", "The alpaca (Lama pacos) is a species of South American camelid mammal.", "The vicuña (Lama vicugna) (/vɪˈkuːnjə/) is one of the two wild South American camelids.", ] queries = ["What is a llama?", "What is a harimau?", "How to fly a kite?"] pairs = list(product(queries, sentences)) model_name = "EmbeddedLLM/bge-reranker-base-onnx-o3-cpu" device = "cpu" provider = "CPUExecutionProvider" tokenizer = AutoTokenizer.from_pretrained(model_name) model = ORTModelForSequenceClassification.from_pretrained( model_name, use_io_binding=True, provider=provider, device_map=device ) inputs = tokenizer( pairs, padding=True, truncation=True, return_tensors="pt", max_length=model.config.max_position_embeddings, ) inputs = inputs.to(device) scores = model(**inputs).logits.view(-1).cpu().numpy() # Sort most similar to least pairs = sorted(zip(pairs, scores), key=lambda x: x[1], reverse=True) for ps in pairs: print(ps) ```

liuhaotian/llava-v1.6-vicuna-7b

liuhaotian

transformers

image-text-to-text

--- inference: false pipeline_tag: image-text-to-text --- <br> <br> # LLaVA Model Card ## Model details **Model type:** LLaVA is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base LLM: [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) **Model date:** LLaVA-v1.6-Vicuna-7B was trained in December 2023. **Paper or resources for more information:** https://llava-vl.github.io/ ## License Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved. **Where to send questions or comments about the model:** https://github.com/haotian-liu/LLaVA/issues ## Intended use **Primary intended uses:** The primary use of LLaVA is research on large multimodal models and chatbots. **Primary intended users:** The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence. ## Training dataset - 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP. - 158K GPT-generated multimodal instruction-following data. - 500K academic-task-oriented VQA data mixture. - 50K GPT-4V data mixture. - 40K ShareGPT data. ## Evaluation dataset A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.

jonatasgrosman/wav2vec2-large-xlsr-53-arabic

jonatasgrosman

transformers

automatic-speech-recognition

--- language: ar datasets: - common_voice - arabic_speech_corpus metrics: - wer - cer tags: - audio - automatic-speech-recognition - speech - xlsr-fine-tuning-week license: apache-2.0 model-index: - name: XLSR Wav2Vec2 Arabic by Jonatas Grosman results: - task: name: Speech Recognition type: automatic-speech-recognition dataset: name: Common Voice ar type: common_voice args: ar metrics: - name: Test WER type: wer value: 39.59 - name: Test CER type: cer value: 18.18 --- # Fine-tuned XLSR-53 large model for speech recognition in Arabic Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Arabic using the train and validation splits of [Common Voice 6.1](https://huggingface.co/datasets/common_voice) and [Arabic Speech Corpus](https://huggingface.co/datasets/arabic_speech_corpus). When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the [OVHcloud](https://www.ovhcloud.com/en/public-cloud/ai-training/) :) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint ## Usage The model can be used directly (without a language model) as follows... Using the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) library: ```python from huggingsound import SpeechRecognitionModel model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-arabic") audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"] transcriptions = model.transcribe(audio_paths) ``` Writing your own inference script: ```python import torch import librosa from datasets import load_dataset from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor LANG_ID = "ar" MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-arabic" SAMPLES = 10 test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]") processor = Wav2Vec2Processor.from_pretrained(MODEL_ID) model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID) # Preprocessing the datasets. # We need to read the audio files as arrays def speech_file_to_array_fn(batch): speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000) batch["speech"] = speech_array batch["sentence"] = batch["sentence"].upper() return batch test_dataset = test_dataset.map(speech_file_to_array_fn) inputs = processor(test_dataset["speech"], sampling_rate=16_000, return_tensors="pt", padding=True) with torch.no_grad(): logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits predicted_ids = torch.argmax(logits, dim=-1) predicted_sentences = processor.batch_decode(predicted_ids) for i, predicted_sentence in enumerate(predicted_sentences): print("-" * 100) print("Reference:", test_dataset[i]["sentence"]) print("Prediction:", predicted_sentence) ``` | Reference | Prediction | | ------------- | ------------- | | ألديك قلم ؟ | ألديك قلم | | ليست هناك مسافة على هذه الأرض أبعد من يوم أمس. | ليست نالك مسافة على هذه الأرض أبعد من يوم الأمس م | | إنك تكبر المشكلة. | إنك تكبر المشكلة | | يرغب أن يلتقي بك. | يرغب أن يلتقي بك | | إنهم لا يعرفون لماذا حتى. | إنهم لا يعرفون لماذا حتى | | سيسعدني مساعدتك أي وقت تحب. | سيسئدنيمساعدتك أي وقد تحب | | أَحَبُّ نظريّة علمية إليّ هي أن حلقات زحل مكونة بالكامل من الأمتعة المفقودة. | أحب نظرية علمية إلي هي أن حل قتزح المكوينا بالكامل من الأمت عن المفقودة | | سأشتري له قلماً. | سأشتري له قلما | | أين المشكلة ؟ | أين المشكل | | وَلِلَّهِ يَسْجُدُ مَا فِي السَّمَاوَاتِ وَمَا فِي الْأَرْضِ مِنْ دَابَّةٍ وَالْمَلَائِكَةُ وَهُمْ لَا يَسْتَكْبِرُونَ | ولله يسجد ما في السماوات وما في الأرض من دابة والملائكة وهم لا يستكبرون | ## Evaluation The model can be evaluated as follows on the Arabic test data of Common Voice. ```python import torch import re import librosa from datasets import load_dataset, load_metric from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor LANG_ID = "ar" MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-arabic" DEVICE = "cuda" CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", "；", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞", "؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]", "{", "}", "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。", "、", "﹂", "﹁", "‧", "～", "﹏", "，", "｛", "｝", "（", "）", "［", "］", "【", "】", "‥", "〽", "『", "』", "〝", "〟", "⟨", "⟩", "〜", "：", "！", "？", "♪", "؛", "/", "\\", "º", "−", "^", "'", "ʻ", "ˆ"] test_dataset = load_dataset("common_voice", LANG_ID, split="test") wer = load_metric("wer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py cer = load_metric("cer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py chars_to_ignore_regex = f"[{re.escape(''.join(CHARS_TO_IGNORE))}]" processor = Wav2Vec2Processor.from_pretrained(MODEL_ID) model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID) model.to(DEVICE) # Preprocessing the datasets. # We need to read the audio files as arrays def speech_file_to_array_fn(batch): with warnings.catch_warnings(): warnings.simplefilter("ignore") speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000) batch["speech"] = speech_array batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"]).upper() return batch test_dataset = test_dataset.map(speech_file_to_array_fn) # Preprocessing the datasets. # We need to read the audio files as arrays def evaluate(batch): inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True) with torch.no_grad(): logits = model(inputs.input_values.to(DEVICE), attention_mask=inputs.attention_mask.to(DEVICE)).logits pred_ids = torch.argmax(logits, dim=-1) batch["pred_strings"] = processor.batch_decode(pred_ids) return batch result = test_dataset.map(evaluate, batched=True, batch_size=8) predictions = [x.upper() for x in result["pred_strings"]] references = [x.upper() for x in result["sentence"]] print(f"WER: {wer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}") print(f"CER: {cer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}") ``` **Test Result**: In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the evaluation script described above on other models as well (on 2021-05-14). Note that the table below may show different results from those already reported, this may have been caused due to some specificity of the other evaluation scripts used. | Model | WER | CER | | ------------- | ------------- | ------------- | | jonatasgrosman/wav2vec2-large-xlsr-53-arabic | **39.59%** | **18.18%** | | bakrianoo/sinai-voice-ar-stt | 45.30% | 21.84% | | othrif/wav2vec2-large-xlsr-arabic | 45.93% | 20.51% | | kmfoda/wav2vec2-large-xlsr-arabic | 54.14% | 26.07% | | mohammed/wav2vec2-large-xlsr-arabic | 56.11% | 26.79% | | anas/wav2vec2-large-xlsr-arabic | 62.02% | 27.09% | | elgeish/wav2vec2-large-xlsr-53-arabic | 100.00% | 100.56% | ## Citation If you want to cite this model you can use this: ```bibtex @misc{grosman2021xlsr53-large-arabic, title={Fine-tuned {XLSR}-53 large model for speech recognition in {A}rabic}, author={Grosman, Jonatas}, howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-arabic}}, year={2021} } ```

microsoft/mdeberta-v3-base

microsoft

transformers

fill-mask

--- language: - multilingual - en - ar - bg - de - el - es - fr - hi - ru - sw - th - tr - ur - vi - zh tags: - deberta - deberta-v3 - mdeberta - fill-mask thumbnail: https://huggingface.co/front/thumbnails/microsoft.png license: mit --- ## DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing [DeBERTa](https://arxiv.org/abs/2006.03654) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa on a majority of NLU tasks with 80GB training data. In [DeBERTa V3](https://arxiv.org/abs/2111.09543), we further improved the efficiency of DeBERTa using ELECTRA-Style pre-training with Gradient Disentangled Embedding Sharing. Compared to DeBERTa, our V3 version significantly improves the model performance on downstream tasks. You can find more technique details about the new model from our [paper](https://arxiv.org/abs/2111.09543). Please check the [official repository](https://github.com/microsoft/DeBERTa) for more implementation details and updates. mDeBERTa is multilingual version of DeBERTa which use the same structure as DeBERTa and was trained with CC100 multilingual data. The mDeBERTa V3 base model comes with 12 layers and a hidden size of 768. It has 86M backbone parameters with a vocabulary containing 250K tokens which introduces 190M parameters in the Embedding layer. This model was trained using the 2.5T CC100 data as XLM-R. #### Fine-tuning on NLU tasks We present the dev results on XNLI with zero-shot cross-lingual transfer setting, i.e. training with English data only, test on other languages. | Model |avg | en | fr| es | de | el | bg | ru |tr |ar |vi | th | zh | hi | sw | ur | |--------------| ----|----|----|---- |-- |-- |-- | -- |-- |-- |-- | -- | -- | -- | -- | -- | | XLM-R-base |76.2 |85.8|79.7|80.7 |78.7 |77.5 |79.6 |78.1 |74.2 |73.8 |76.5 |74.6 |76.7| 72.4| 66.5| 68.3| | mDeBERTa-base|**79.8**+/-0.2|**88.2**|**82.6**|**84.4** |**82.7** |**82.3** |**82.4** |**80.8** |**79.5** |**78.5** |**78.1** |**76.4** |**79.5**| **75.9**| **73.9**| **72.4**| #### Fine-tuning with HF transformers ```bash #!/bin/bash cd transformers/examples/pytorch/text-classification/ pip install datasets output_dir="ds_results" num_gpus=8 batch_size=4 python -m torch.distributed.launch --nproc_per_node=${num_gpus} \ run_xnli.py \ --model_name_or_path microsoft/mdeberta-v3-base \ --task_name $TASK_NAME \ --do_train \ --do_eval \ --train_language en \ --language en \ --evaluation_strategy steps \ --max_seq_length 256 \ --warmup_steps 3000 \ --per_device_train_batch_size ${batch_size} \ --learning_rate 2e-5 \ --num_train_epochs 6 \ --output_dir $output_dir \ --overwrite_output_dir \ --logging_steps 1000 \ --logging_dir $output_dir ``` ### Citation If you find DeBERTa useful for your work, please cite the following papers: ``` latex @misc{he2021debertav3, title={DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing}, author={Pengcheng He and Jianfeng Gao and Weizhu Chen}, year={2021}, eprint={2111.09543}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ``` latex @inproceedings{ he2021deberta, title={DEBERTA: DECODING-ENHANCED BERT WITH DISENTANGLED ATTENTION}, author={Pengcheng He and Xiaodong Liu and Jianfeng Gao and Weizhu Chen}, booktitle={International Conference on Learning Representations}, year={2021}, url={https://openreview.net/forum?id=XPZIaotutsD} } ```

MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF

MaziyarPanahi

transformers

text-generation

--- tags: - quantized - 2-bit - 3-bit - 4-bit - 5-bit - 6-bit - 8-bit - GGUF - transformers - safetensors - mistral - text-generation - conversational - license:apache-2.0 - autotrain_compatible - endpoints_compatible - text-generation-inference - region:us - text-generation model_name: Mistral-7B-Instruct-v0.3-GGUF base_model: mistralai/Mistral-7B-Instruct-v0.3 inference: false model_creator: mistralai pipeline_tag: text-generation quantized_by: MaziyarPanahi --- # [MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF](https://huggingface.co/MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF) - Model creator: [mistralai](https://huggingface.co/mistralai) - Original model: [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) ## Description [MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF](https://huggingface.co/MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF) contains GGUF format model files for [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3). ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. ## Special thanks 🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.

distilbert/distilbert-base-cased

distilbert

transformers

fill-mask

--- language: en license: apache-2.0 datasets: - bookcorpus - wikipedia --- # Model Card for DistilBERT base model (cased) This model is a distilled version of the [BERT base model](https://huggingface.co/bert-base-cased). It was introduced in [this paper](https://arxiv.org/abs/1910.01108). The code for the distillation process can be found [here](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation). This model is cased: it does make a difference between english and English. All the training details on the pre-training, the uses, limitations and potential biases (included below) are the same as for [DistilBERT-base-uncased](https://huggingface.co/distilbert-base-uncased). We highly encourage to check it if you want to know more. ## Model description DistilBERT is a transformers model, smaller and faster than BERT, which was pretrained on the same corpus in a self-supervised fashion, using the BERT base model as a teacher. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts using the BERT base model. More precisely, it was pretrained with three objectives: - Distillation loss: the model was trained to return the same probabilities as the BERT base model. - Masked language modeling (MLM): this is part of the original training loss of the BERT base model. When taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence. - Cosine embedding loss: the model was also trained to generate hidden states as close as possible as the BERT base model. This way, the model learns the same inner representation of the English language than its teacher model, while being faster for inference or downstream tasks. ## Intended uses & limitations You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=distilbert) to look for fine-tuned versions on a task that interests you. Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering. For tasks such as text generation you should look at model like GPT2. ### How to use You can use this model directly with a pipeline for masked language modeling: ```python >>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='distilbert-base-uncased') >>> unmasker("Hello I'm a [MASK] model.") [{'sequence': "[CLS] hello i'm a role model. [SEP]", 'score': 0.05292855575680733, 'token': 2535, 'token_str': 'role'}, {'sequence': "[CLS] hello i'm a fashion model. [SEP]", 'score': 0.03968575969338417, 'token': 4827, 'token_str': 'fashion'}, {'sequence': "[CLS] hello i'm a business model. [SEP]", 'score': 0.034743521362543106, 'token': 2449, 'token_str': 'business'}, {'sequence': "[CLS] hello i'm a model model. [SEP]", 'score': 0.03462274372577667, 'token': 2944, 'token_str': 'model'}, {'sequence': "[CLS] hello i'm a modeling model. [SEP]", 'score': 0.018145186826586723, 'token': 11643, 'token_str': 'modeling'}] ``` Here is how to use this model to get the features of a given text in PyTorch: ```python from transformers import DistilBertTokenizer, DistilBertModel tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased') model = DistilBertModel.from_pretrained("distilbert-base-uncased") text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='pt') output = model(**encoded_input) ``` and in TensorFlow: ```python from transformers import DistilBertTokenizer, TFDistilBertModel tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased') model = TFDistilBertModel.from_pretrained("distilbert-base-uncased") text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='tf') output = model(encoded_input) ``` ### Limitations and bias Even if the training data used for this model could be characterized as fairly neutral, this model can have biased predictions. It also inherits some of [the bias of its teacher model](https://huggingface.co/bert-base-uncased#limitations-and-bias). ```python >>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='distilbert-base-uncased') >>> unmasker("The White man worked as a [MASK].") [{'sequence': '[CLS] the white man worked as a blacksmith. [SEP]', 'score': 0.1235365942120552, 'token': 20987, 'token_str': 'blacksmith'}, {'sequence': '[CLS] the white man worked as a carpenter. [SEP]', 'score': 0.10142576694488525, 'token': 10533, 'token_str': 'carpenter'}, {'sequence': '[CLS] the white man worked as a farmer. [SEP]', 'score': 0.04985016956925392, 'token': 7500, 'token_str': 'farmer'}, {'sequence': '[CLS] the white man worked as a miner. [SEP]', 'score': 0.03932540491223335, 'token': 18594, 'token_str': 'miner'}, {'sequence': '[CLS] the white man worked as a butcher. [SEP]', 'score': 0.03351764753460884, 'token': 14998, 'token_str': 'butcher'}] >>> unmasker("The Black woman worked as a [MASK].") [{'sequence': '[CLS] the black woman worked as a waitress. [SEP]', 'score': 0.13283951580524445, 'token': 13877, 'token_str': 'waitress'}, {'sequence': '[CLS] the black woman worked as a nurse. [SEP]', 'score': 0.12586183845996857, 'token': 6821, 'token_str': 'nurse'}, {'sequence': '[CLS] the black woman worked as a maid. [SEP]', 'score': 0.11708822101354599, 'token': 10850, 'token_str': 'maid'}, {'sequence': '[CLS] the black woman worked as a prostitute. [SEP]', 'score': 0.11499975621700287, 'token': 19215, 'token_str': 'prostitute'}, {'sequence': '[CLS] the black woman worked as a housekeeper. [SEP]', 'score': 0.04722772538661957, 'token': 22583, 'token_str': 'housekeeper'}] ``` This bias will also affect all fine-tuned versions of this model. ## Training data DistilBERT pretrained on the same data as BERT, which is [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038 unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and headers). ## Training procedure ### Preprocessing The texts are lowercased and tokenized using WordPiece and a vocabulary size of 30,000. The inputs of the model are then of the form: ``` [CLS] Sentence A [SEP] Sentence B [SEP] ``` With probability 0.5, sentence A and sentence B correspond to two consecutive sentences in the original corpus and in the other cases, it's another random sentence in the corpus. Note that what is considered a sentence here is a consecutive span of text usually longer than a single sentence. The only constrain is that the result with the two "sentences" has a combined length of less than 512 tokens. The details of the masking procedure for each sentence are the following: - 15% of the tokens are masked. - In 80% of the cases, the masked tokens are replaced by `[MASK]`. - In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace. - In the 10% remaining cases, the masked tokens are left as is. ### Pretraining The model was trained on 8 16 GB V100 for 90 hours. See the [training code](https://github.com/huggingface/transformers/tree/master/examples/distillation) for all hyperparameters details. ## Evaluation results When fine-tuned on downstream tasks, this model achieves the following results: Glue test results: | Task | MNLI | QQP | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE | |:----:|:----:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:| | | 81.5 | 87.8 | 88.2 | 90.4 | 47.2 | 85.5 | 85.6 | 60.6 | ### BibTeX entry and citation info ```bibtex @article{Sanh2019DistilBERTAD, title={DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter}, author={Victor Sanh and Lysandre Debut and Julien Chaumond and Thomas Wolf}, journal={ArXiv}, year={2019}, volume={abs/1910.01108} } ``` <a href="https://huggingface.co/exbert/?model=distilbert-base-uncased"> <img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png"> </a>

charsiu/g2p_multilingual_byT5_small_100

charsiu

transformers

text2text-generation

Entry not found

sentence-transformers/multi-qa-mpnet-base-dot-v1

sentence-transformers

sentence-transformers

sentence-similarity

--- language: - en library_name: sentence-transformers tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers datasets: - flax-sentence-embeddings/stackexchange_xml - ms_marco - gooaq - yahoo_answers_topics - search_qa - eli5 - natural_questions - trivia_qa - embedding-data/QQP - embedding-data/PAQ_pairs - embedding-data/Amazon-QA - embedding-data/WikiAnswers pipeline_tag: sentence-similarity --- # multi-qa-mpnet-base-dot-v1 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and was designed for **semantic search**. It has been trained on 215M (question, answer) pairs from diverse sources. For an introduction to semantic search, have a look at: [SBERT.net - Semantic Search](https://www.sbert.net/examples/applications/semantic-search/README.html) ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer, util query = "How many people live in London?" docs = ["Around 9 Million people live in London", "London is known for its financial district"] #Load the model model = SentenceTransformer('sentence-transformers/multi-qa-mpnet-base-dot-v1') #Encode query and documents query_emb = model.encode(query) doc_emb = model.encode(docs) #Compute dot score between query and all document embeddings scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist() #Combine docs & scores doc_score_pairs = list(zip(docs, scores)) #Sort by decreasing score doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True) #Output passages & scores for doc, score in doc_score_pairs: print(score, doc) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the correct pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch #CLS Pooling - Take output from first token def cls_pooling(model_output): return model_output.last_hidden_state[:,0] #Encode text def encode(texts): # Tokenize sentences encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(**encoded_input, return_dict=True) # Perform pooling embeddings = cls_pooling(model_output) return embeddings # Sentences we want sentence embeddings for query = "How many people live in London?" docs = ["Around 9 Million people live in London", "London is known for its financial district"] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/multi-qa-mpnet-base-dot-v1") model = AutoModel.from_pretrained("sentence-transformers/multi-qa-mpnet-base-dot-v1") #Encode query and docs query_emb = encode(query) doc_emb = encode(docs) #Compute dot score between query and all document embeddings scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist() #Combine docs & scores doc_score_pairs = list(zip(docs, scores)) #Sort by decreasing score doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True) #Output passages & scores for doc, score in doc_score_pairs: print(score, doc) ``` ## Technical Details In the following some technical details how this model must be used: | Setting | Value | | --- | :---: | | Dimensions | 768 | | Produces normalized embeddings | No | | Pooling-Method | CLS pooling | | Suitable score functions | dot-product (e.g. `util.dot_score`) | ---- ## Background The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset. We developped this model during the [Community week using JAX/Flax for NLP & CV](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104), organized by Hugging Face. We developped this model as part of the project: [Train the Best Sentence Embedding Model Ever with 1B Training Pairs](https://discuss.huggingface.co/t/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs/7354). We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks. ## Intended uses Our model is intented to be used for semantic search: It encodes queries / questions and text paragraphs in a dense vector space. It finds relevant documents for the given passages. Note that there is a limit of 512 word pieces: Text longer than that will be truncated. Further note that the model was just trained on input text up to 250 word pieces. It might not work well for longer text. ## Training procedure The full training script is accessible in this current repository: `train_script.py`. ### Pre-training We use the pretrained [`mpnet-base`](https://huggingface.co/microsoft/mpnet-base) model. Please refer to the model card for more detailed information about the pre-training procedure. #### Training We use the concatenation from multiple datasets to fine-tune our model. In total we have about 215M (question, answer) pairs. We sampled each dataset given a weighted probability which configuration is detailed in the `data_config.json` file. The model was trained with [MultipleNegativesRankingLoss](https://www.sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) using CLS-pooling, dot-product as similarity function, and a scale of 1. | Dataset | Number of training tuples | |--------------------------------------------------------|:--------------------------:| | [WikiAnswers](https://github.com/afader/oqa#wikianswers-corpus) Duplicate question pairs from WikiAnswers | 77,427,422 | | [PAQ](https://github.com/facebookresearch/PAQ) Automatically generated (Question, Paragraph) pairs for each paragraph in Wikipedia | 64,371,441 | | [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Body) pairs from all StackExchanges | 25,316,456 | | [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Answer) pairs from all StackExchanges | 21,396,559 | | [MS MARCO](https://microsoft.github.io/msmarco/) Triplets (query, answer, hard_negative) for 500k queries from Bing search engine | 17,579,773 | | [GOOAQ: Open Question Answering with Diverse Answer Types](https://github.com/allenai/gooaq) (query, answer) pairs for 3M Google queries and Google featured snippet | 3,012,496 | | [Amazon-QA](http://jmcauley.ucsd.edu/data/amazon/qa/) (Question, Answer) pairs from Amazon product pages | 2,448,839 | [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Answer) pairs from Yahoo Answers | 1,198,260 | | [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Question, Answer) pairs from Yahoo Answers | 681,164 | | [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Question) pairs from Yahoo Answers | 659,896 | | [SearchQA](https://huggingface.co/datasets/search_qa) (Question, Answer) pairs for 140k questions, each with Top5 Google snippets on that question | 582,261 | | [ELI5](https://huggingface.co/datasets/eli5) (Question, Answer) pairs from Reddit ELI5 (explainlikeimfive) | 325,475 | | [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions pairs (titles) | 304,525 | | [Quora Question Triplets](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) (Question, Duplicate_Question, Hard_Negative) triplets for Quora Questions Pairs dataset | 103,663 | | [Natural Questions (NQ)](https://ai.google.com/research/NaturalQuestions) (Question, Paragraph) pairs for 100k real Google queries with relevant Wikipedia paragraph | 100,231 | | [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/) (Question, Paragraph) pairs from SQuAD2.0 dataset | 87,599 | | [TriviaQA](https://huggingface.co/datasets/trivia_qa) (Question, Evidence) pairs | 73,346 | | **Total** | **214,988,242** |

cardiffnlp/twitter-xlm-roberta-base-sentiment

cardiffnlp

transformers

text-classification

--- language: multilingual widget: - text: "🤗" - text: "T'estimo! ❤️" - text: "I love you!" - text: "I hate you 🤮" - text: "Mahal kita!" - text: "사랑해!" - text: "난 너가 싫어" - text: "😍😍😍" --- # twitter-XLM-roBERTa-base for Sentiment Analysis This is a multilingual XLM-roBERTa-base model trained on ~198M tweets and finetuned for sentiment analysis. The sentiment fine-tuning was done on 8 languages (Ar, En, Fr, De, Hi, It, Sp, Pt) but it can be used for more languages (see paper for details). - Paper: [XLM-T: A Multilingual Language Model Toolkit for Twitter](https://arxiv.org/abs/2104.12250). - Git Repo: [XLM-T official repository](https://github.com/cardiffnlp/xlm-t). This model has been integrated into the [TweetNLP library](https://github.com/cardiffnlp/tweetnlp). ## Example Pipeline ```python from transformers import pipeline model_path = "cardiffnlp/twitter-xlm-roberta-base-sentiment" sentiment_task = pipeline("sentiment-analysis", model=model_path, tokenizer=model_path) sentiment_task("T'estimo!") ``` ``` [{'label': 'Positive', 'score': 0.6600581407546997}] ``` ## Full classification example ```python from transformers import AutoModelForSequenceClassification from transformers import TFAutoModelForSequenceClassification from transformers import AutoTokenizer, AutoConfig import numpy as np from scipy.special import softmax # Preprocess text (username and link placeholders) def preprocess(text): new_text = [] for t in text.split(" "): t = '@user' if t.startswith('@') and len(t) > 1 else t t = 'http' if t.startswith('http') else t new_text.append(t) return " ".join(new_text) MODEL = f"cardiffnlp/twitter-xlm-roberta-base-sentiment" tokenizer = AutoTokenizer.from_pretrained(MODEL) config = AutoConfig.from_pretrained(MODEL) # PT model = AutoModelForSequenceClassification.from_pretrained(MODEL) model.save_pretrained(MODEL) text = "Good night 😊" text = preprocess(text) encoded_input = tokenizer(text, return_tensors='pt') output = model(**encoded_input) scores = output[0][0].detach().numpy() scores = softmax(scores) # # TF # model = TFAutoModelForSequenceClassification.from_pretrained(MODEL) # model.save_pretrained(MODEL) # text = "Good night 😊" # encoded_input = tokenizer(text, return_tensors='tf') # output = model(encoded_input) # scores = output[0][0].numpy() # scores = softmax(scores) # Print labels and scores ranking = np.argsort(scores) ranking = ranking[::-1] for i in range(scores.shape[0]): l = config.id2label[ranking[i]] s = scores[ranking[i]] print(f"{i+1}) {l} {np.round(float(s), 4)}") ``` Output: ``` 1) Positive 0.7673 2) Neutral 0.2015 3) Negative 0.0313 ``` ### Reference ``` @inproceedings{barbieri-etal-2022-xlm, title = "{XLM}-{T}: Multilingual Language Models in {T}witter for Sentiment Analysis and Beyond", author = "Barbieri, Francesco and Espinosa Anke, Luis and Camacho-Collados, Jose", booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference", month = jun, year = "2022", address = "Marseille, France", publisher = "European Language Resources Association", url = "https://aclanthology.org/2022.lrec-1.27", pages = "258--266" } ```

jonatasgrosman/wav2vec2-large-xlsr-53-dutch

jonatasgrosman

transformers

automatic-speech-recognition

--- language: nl license: apache-2.0 datasets: - common_voice - mozilla-foundation/common_voice_6_0 metrics: - wer - cer tags: - audio - automatic-speech-recognition - hf-asr-leaderboard - mozilla-foundation/common_voice_6_0 - nl - robust-speech-event - speech - xlsr-fine-tuning-week model-index: - name: XLSR Wav2Vec2 Dutch by Jonatas Grosman results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Common Voice nl type: common_voice args: nl metrics: - name: Test WER type: wer value: 15.72 - name: Test CER type: cer value: 5.35 - name: Test WER (+LM) type: wer value: 12.84 - name: Test CER (+LM) type: cer value: 4.64 - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Robust Speech Event - Dev Data type: speech-recognition-community-v2/dev_data args: nl metrics: - name: Dev WER type: wer value: 35.79 - name: Dev CER type: cer value: 17.67 - name: Dev WER (+LM) type: wer value: 31.54 - name: Dev CER (+LM) type: cer value: 16.37 --- # Fine-tuned XLSR-53 large model for speech recognition in Dutch Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Dutch using the train and validation splits of [Common Voice 6.1](https://huggingface.co/datasets/common_voice) and [CSS10](https://github.com/Kyubyong/css10). When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the [OVHcloud](https://www.ovhcloud.com/en/public-cloud/ai-training/) :) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint ## Usage The model can be used directly (without a language model) as follows... Using the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) library: ```python from huggingsound import SpeechRecognitionModel model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-dutch") audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"] transcriptions = model.transcribe(audio_paths) ``` Writing your own inference script: ```python import torch import librosa from datasets import load_dataset from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor LANG_ID = "nl" MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-dutch" SAMPLES = 10 test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]") processor = Wav2Vec2Processor.from_pretrained(MODEL_ID) model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID) # Preprocessing the datasets. # We need to read the audio files as arrays def speech_file_to_array_fn(batch): speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000) batch["speech"] = speech_array batch["sentence"] = batch["sentence"].upper() return batch test_dataset = test_dataset.map(speech_file_to_array_fn) inputs = processor(test_dataset["speech"], sampling_rate=16_000, return_tensors="pt", padding=True) with torch.no_grad(): logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits predicted_ids = torch.argmax(logits, dim=-1) predicted_sentences = processor.batch_decode(predicted_ids) for i, predicted_sentence in enumerate(predicted_sentences): print("-" * 100) print("Reference:", test_dataset[i]["sentence"]) print("Prediction:", predicted_sentence) ``` | Reference | Prediction | | ------------- | ------------- | | DE ABORIGINALS ZIJN DE OORSPRONKELIJKE BEWONERS VAN AUSTRALIË. | DE ABBORIGENALS ZIJN DE OORSPRONKELIJKE BEWONERS VAN AUSTRALIË | | MIJN TOETSENBORD ZIT VOL STOF. | MIJN TOETSENBORD ZIT VOL STOF | | ZE HAD DE BANK BESCHADIGD MET HAAR SKATEBOARD. | ZE HAD DE BANK BESCHADIGD MET HAAR SCHEETBOORD | | WAAR LAAT JIJ JE ONDERHOUD DOEN? | WAAR LAAT JIJ HET ONDERHOUD DOEN | | NA HET LEZEN VAN VELE BEOORDELINGEN HAD ZE EINDELIJK HAAR OOG LATEN VALLEN OP EEN LAPTOP MET EEN QWERTY TOETSENBORD. | NA HET LEZEN VAN VELE BEOORDELINGEN HAD ZE EINDELIJK HAAR OOG LATEN VALLEN OP EEN LAPTOP MET EEN QUERTITOETSEMBORD | | DE TAMPONS ZIJN OP. | DE TAPONT ZIJN OP | | MARIJKE KENT OLIVIER NU AL MEER DAN TWEE JAAR. | MAARRIJKEN KENT OLIEVIER NU AL MEER DAN TWEE JAAR | | HET VOEREN VAN BROOD AAN EENDEN IS EIGENLIJK ONGEZOND VOOR DE BEESTEN. | HET VOEREN VAN BEUROT AAN EINDEN IS EIGENLIJK ONGEZOND VOOR DE BEESTEN | | PARKET MOET JE STOFZUIGEN, TEGELS MOET JE DWEILEN. | PARKET MOET JE STOF ZUIGEN MAAR TEGELS MOET JE DWEILEN | | IN ONZE BUURT KENT IEDEREEN ELKAAR. | IN ONZE BUURT KENT IEDEREEN ELKAAR | ## Evaluation 1. To evaluate on `mozilla-foundation/common_voice_6_0` with split `test` ```bash python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-dutch --dataset mozilla-foundation/common_voice_6_0 --config nl --split test ``` 2. To evaluate on `speech-recognition-community-v2/dev_data` ```bash python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-dutch --dataset speech-recognition-community-v2/dev_data --config nl --split validation --chunk_length_s 5.0 --stride_length_s 1.0 ``` ## Citation If you want to cite this model you can use this: ```bibtex @misc{grosman2021xlsr53-large-dutch, title={Fine-tuned {XLSR}-53 large model for speech recognition in {D}utch}, author={Grosman, Jonatas}, howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-dutch}}, year={2021} } ```

stabilityai/stable-diffusion-2-1-base

stabilityai

diffusers

text-to-image

--- license: openrail++ tags: - stable-diffusion - text-to-image --- # Stable Diffusion v2-1-base Model Card This model card focuses on the model associated with the Stable Diffusion v2-1-base model. This `stable-diffusion-2-1-base` model fine-tunes [stable-diffusion-2-base](https://huggingface.co/stabilityai/stable-diffusion-2-base) (`512-base-ema.ckpt`) with 220k extra steps taken, with `punsafe=0.98` on the same dataset. - Use it with the [`stablediffusion`](https://github.com/Stability-AI/stablediffusion) repository: download the `v2-1_512-ema-pruned.ckpt` [here](https://huggingface.co/stabilityai/stable-diffusion-2-1-base/resolve/main/v2-1_512-ema-pruned.ckpt). - Use it with 🧨 [`diffusers`](#examples) ## Model Details - **Developed by:** Robin Rombach, Patrick Esser - **Model type:** Diffusion-based text-to-image generation model - **Language(s):** English - **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL) - **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses a fixed, pretrained text encoder ([OpenCLIP-ViT/H](https://github.com/mlfoundations/open_clip)). - **Resources for more information:** [GitHub Repository](https://github.com/Stability-AI/). - **Cite as:** @InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} } ## Examples Using the [🤗's Diffusers library](https://github.com/huggingface/diffusers) to run Stable Diffusion 2 in a simple and efficient manner. ```bash pip install diffusers transformers accelerate scipy safetensors ``` Running the pipeline (if you don't swap the scheduler it will run with the default PNDM/PLMS scheduler, in this example we are swapping it to EulerDiscreteScheduler): ```python from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler import torch model_id = "stabilityai/stable-diffusion-2-1-base" scheduler = EulerDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler") pipe = StableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, torch_dtype=torch.float16) pipe = pipe.to("cuda") prompt = "a photo of an astronaut riding a horse on mars" image = pipe(prompt).images[0] image.save("astronaut_rides_horse.png") ``` **Notes**: - Despite not being a dependency, we highly recommend you to install [xformers](https://github.com/facebookresearch/xformers) for memory efficient attention (better performance) - If you have low GPU RAM available, make sure to add a `pipe.enable_attention_slicing()` after sending it to `cuda` for less VRAM usage (to the cost of speed) # Uses ## Direct Use The model is intended for research purposes only. Possible research areas and tasks include - Safe deployment of models which have the potential to generate harmful content. - Probing and understanding the limitations and biases of generative models. - Generation of artworks and use in design and other artistic processes. - Applications in educational or creative tools. - Research on generative models. Excluded uses are described below. ### Misuse, Malicious Use, and Out-of-Scope Use _Note: This section is originally taken from the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini), was used for Stable Diffusion v1, but applies in the same way to Stable Diffusion v2_. The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes. #### Out-of-Scope Use The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model. #### Misuse and Malicious Use Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to: - Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc. - Intentionally promoting or propagating discriminatory content or harmful stereotypes. - Impersonating individuals without their consent. - Sexual content without consent of the people who might see it. - Mis- and disinformation - Representations of egregious violence and gore - Sharing of copyrighted or licensed material in violation of its terms of use. - Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use. ## Limitations and Bias ### Limitations - The model does not achieve perfect photorealism - The model cannot render legible text - The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere” - Faces and people in general may not be generated properly. - The model was trained mainly with English captions and will not work as well in other languages. - The autoencoding part of the model is lossy - The model was trained on a subset of the large-scale dataset [LAION-5B](https://laion.ai/blog/laion-5b/), which contains adult, violent and sexual content. To partially mitigate this, we have filtered the dataset using LAION's NFSW detector (see Training section). ### Bias While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases. Stable Diffusion vw was primarily trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/), which consists of images that are limited to English descriptions. Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for. This affects the overall output of the model, as white and western cultures are often set as the default. Further, the ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts. Stable Diffusion v2 mirrors and exacerbates biases to such a degree that viewer discretion must be advised irrespective of the input or its intent. ## Training **Training Data** The model developers used the following dataset for training the model: - LAION-5B and subsets (details below). The training data is further filtered using LAION's NSFW detector, with a "p_unsafe" score of 0.1 (conservative). For more details, please refer to LAION-5B's [NeurIPS 2022](https://openreview.net/forum?id=M3Y74vmsMcY) paper and reviewer discussions on the topic. **Training Procedure** Stable Diffusion v2 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training, - Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4 - Text prompts are encoded through the OpenCLIP-ViT/H text-encoder. - The output of the text encoder is fed into the UNet backbone of the latent diffusion model via cross-attention. - The loss is a reconstruction objective between the noise that was added to the latent and the prediction made by the UNet. We also use the so-called _v-objective_, see https://arxiv.org/abs/2202.00512. We currently provide the following checkpoints, for various versions: ### Version 2.1 - `512-base-ema.ckpt`: Fine-tuned on `512-base-ema.ckpt` 2.0 with 220k extra steps taken, with `punsafe=0.98` on the same dataset. - `768-v-ema.ckpt`: Resumed from `768-v-ema.ckpt` 2.0 with an additional 55k steps on the same dataset (`punsafe=0.1`), and then fine-tuned for another 155k extra steps with `punsafe=0.98`. ### Version 2.0 - `512-base-ema.ckpt`: 550k steps at resolution `256x256` on a subset of [LAION-5B](https://laion.ai/blog/laion-5b/) filtered for explicit pornographic material, using the [LAION-NSFW classifier](https://github.com/LAION-AI/CLIP-based-NSFW-Detector) with `punsafe=0.1` and an [aesthetic score](https://github.com/christophschuhmann/improved-aesthetic-predictor) >= `4.5`. 850k steps at resolution `512x512` on the same dataset with resolution `>= 512x512`. - `768-v-ema.ckpt`: Resumed from `512-base-ema.ckpt` and trained for 150k steps using a [v-objective](https://arxiv.org/abs/2202.00512) on the same dataset. Resumed for another 140k steps on a `768x768` subset of our dataset. - `512-depth-ema.ckpt`: Resumed from `512-base-ema.ckpt` and finetuned for 200k steps. Added an extra input channel to process the (relative) depth prediction produced by [MiDaS](https://github.com/isl-org/MiDaS) (`dpt_hybrid`) which is used as an additional conditioning. The additional input channels of the U-Net which process this extra information were zero-initialized. - `512-inpainting-ema.ckpt`: Resumed from `512-base-ema.ckpt` and trained for another 200k steps. Follows the mask-generation strategy presented in [LAMA](https://github.com/saic-mdal/lama) which, in combination with the latent VAE representations of the masked image, are used as an additional conditioning. The additional input channels of the U-Net which process this extra information were zero-initialized. The same strategy was used to train the [1.5-inpainting checkpoint](https://github.com/saic-mdal/lama). - `x4-upscaling-ema.ckpt`: Trained for 1.25M steps on a 10M subset of LAION containing images `>2048x2048`. The model was trained on crops of size `512x512` and is a text-guided [latent upscaling diffusion model](https://arxiv.org/abs/2112.10752). In addition to the textual input, it receives a `noise_level` as an input parameter, which can be used to add noise to the low-resolution input according to a [predefined diffusion schedule](configs/stable-diffusion/x4-upscaling.yaml). - **Hardware:** 32 x 8 x A100 GPUs - **Optimizer:** AdamW - **Gradient Accumulations**: 1 - **Batch:** 32 x 8 x 2 x 4 = 2048 - **Learning rate:** warmup to 0.0001 for 10,000 steps and then kept constant ## Evaluation Results Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0) and 50 steps DDIM sampling steps show the relative improvements of the checkpoints:  Evaluated using 50 DDIM steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution. Not optimized for FID scores. ## Environmental Impact **Stable Diffusion v1** **Estimated Emissions** Based on that information, we estimate the following CO2 emissions using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact. - **Hardware Type:** A100 PCIe 40GB - **Hours used:** 200000 - **Cloud Provider:** AWS - **Compute Region:** US-east - **Carbon Emitted (Power consumption x Time x Carbon produced based on location of power grid):** 15000 kg CO2 eq. ## Citation @InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} } *This model card was written by: Robin Rombach, Patrick Esser and David Ha and is based on the [Stable Diffusion v1](https://github.com/CompVis/stable-diffusion/blob/main/Stable_Diffusion_v1_Model_Card.md) and [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).*

stabilityai/stable-diffusion-xl-refiner-1.0

stabilityai

diffusers

image-to-image

--- license: openrail++ tags: - stable-diffusion - image-to-image --- # SD-XL 1.0-refiner Model Card  ## Model  [SDXL](https://arxiv.org/abs/2307.01952) consists of an [ensemble of experts](https://arxiv.org/abs/2211.01324) pipeline for latent diffusion: In a first step, the base model (available here: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) is used to generate (noisy) latents, which are then further processed with a refinement model specialized for the final denoising steps. Note that the base model can be used as a standalone module. Alternatively, we can use a two-stage pipeline as follows: First, the base model is used to generate latents of the desired output size. In the second step, we use a specialized high-resolution model and apply a technique called SDEdit (https://arxiv.org/abs/2108.01073, also known as "img2img") to the latents generated in the first step, using the same prompt. This technique is slightly slower than the first one, as it requires more function evaluations. Source code is available at https://github.com/Stability-AI/generative-models . ### Model Description - **Developed by:** Stability AI - **Model type:** Diffusion-based text-to-image generative model - **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/blob/main/LICENSE.md) - **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses two fixed, pretrained text encoders ([OpenCLIP-ViT/G](https://github.com/mlfoundations/open_clip) and [CLIP-ViT/L](https://github.com/openai/CLIP/tree/main)). - **Resources for more information:** Check out our [GitHub Repository](https://github.com/Stability-AI/generative-models) and the [SDXL report on arXiv](https://arxiv.org/abs/2307.01952). ### Model Sources For research purposes, we recommned our `generative-models` Github repository (https://github.com/Stability-AI/generative-models), which implements the most popoular diffusion frameworks (both training and inference) and for which new functionalities like distillation will be added over time. [Clipdrop](https://clipdrop.co/stable-diffusion) provides free SDXL inference. - **Repository:** https://github.com/Stability-AI/generative-models - **Demo:** https://clipdrop.co/stable-diffusion ## Evaluation  The chart above evaluates user preference for SDXL (with and without refinement) over SDXL 0.9 and Stable Diffusion 1.5 and 2.1. The SDXL base model performs significantly better than the previous variants, and the model combined with the refinement module achieves the best overall performance. ### 🧨 Diffusers Make sure to upgrade diffusers to >= 0.18.0: ``` pip install diffusers --upgrade ``` In addition make sure to install `transformers`, `safetensors`, `accelerate` as well as the invisible watermark: ``` pip install invisible_watermark transformers accelerate safetensors ``` Yon can then use the refiner to improve images. ```py import torch from diffusers import StableDiffusionXLImg2ImgPipeline from diffusers.utils import load_image pipe = StableDiffusionXLImg2ImgPipeline.from_pretrained( "stabilityai/stable-diffusion-xl-refiner-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True ) pipe = pipe.to("cuda") url = "https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/aa_xl/000000009.png" init_image = load_image(url).convert("RGB") prompt = "a photo of an astronaut riding a horse on mars" image = pipe(prompt, image=init_image).images ``` When using `torch >= 2.0`, you can improve the inference speed by 20-30% with torch.compile. Simple wrap the unet with torch compile before running the pipeline: ```py pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True) ``` If you are limited by GPU VRAM, you can enable *cpu offloading* by calling `pipe.enable_model_cpu_offload` instead of `.to("cuda")`: ```diff - pipe.to("cuda") + pipe.enable_model_cpu_offload() ``` For more advanced use cases, please have a look at [the docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/stable_diffusion_xl). ## Uses ### Direct Use The model is intended for research purposes only. Possible research areas and tasks include - Generation of artworks and use in design and other artistic processes. - Applications in educational or creative tools. - Research on generative models. - Safe deployment of models which have the potential to generate harmful content. - Probing and understanding the limitations and biases of generative models. Excluded uses are described below. ### Out-of-Scope Use The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model. ## Limitations and Bias ### Limitations - The model does not achieve perfect photorealism - The model cannot render legible text - The model struggles with more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere” - Faces and people in general may not be generated properly. - The autoencoding part of the model is lossy. ### Bias While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.

Supabase/gte-small

Supabase

transformers.js

feature-extraction

--- pipeline_tag: feature-extraction library_name: "transformers.js" language: - en license: mit --- _Fork of https://huggingface.co/thenlper/gte-small with ONNX weights to be compatible with Transformers.js. See [JavaScript usage](#javascript)._ --- # gte-small General Text Embeddings (GTE) model. The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including [GTE-large](https://huggingface.co/thenlper/gte-large), [GTE-base](https://huggingface.co/thenlper/gte-base), and [GTE-small](https://huggingface.co/thenlper/gte-small). The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including **information retrieval**, **semantic textual similarity**, **text reranking**, etc. ## Metrics Performance of GTE models were compared with other popular text embedding models on the MTEB benchmark. For more detailed comparison results, please refer to the [MTEB leaderboard](https://huggingface.co/spaces/mteb/leaderboard). | Model Name | Model Size (GB) | Dimension | Sequence Length | Average (56) | Clustering (11) | Pair Classification (3) | Reranking (4) | Retrieval (15) | STS (10) | Summarization (1) | Classification (12) | |:----:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:| | [**gte-large**](https://huggingface.co/thenlper/gte-large) | 0.67 | 1024 | 512 | **63.13** | 46.84 | 85.00 | 59.13 | 52.22 | 83.35 | 31.66 | 73.33 | | [**gte-base**](https://huggingface.co/thenlper/gte-base) | 0.22 | 768 | 512 | **62.39** | 46.2 | 84.57 | 58.61 | 51.14 | 82.3 | 31.17 | 73.01 | | [e5-large-v2](https://huggingface.co/intfloat/e5-large-v2) | 1.34 | 1024| 512 | 62.25 | 44.49 | 86.03 | 56.61 | 50.56 | 82.05 | 30.19 | 75.24 | | [e5-base-v2](https://huggingface.co/intfloat/e5-base-v2) | 0.44 | 768 | 512 | 61.5 | 43.80 | 85.73 | 55.91 | 50.29 | 81.05 | 30.28 | 73.84 | | [**gte-small**](https://huggingface.co/thenlper/gte-small) | 0.07 | 384 | 512 | **61.36** | 44.89 | 83.54 | 57.7 | 49.46 | 82.07 | 30.42 | 72.31 | | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) | - | 1536 | 8192 | 60.99 | 45.9 | 84.89 | 56.32 | 49.25 | 80.97 | 30.8 | 70.93 | | [e5-small-v2](https://huggingface.co/intfloat/e5-base-v2) | 0.13 | 384 | 512 | 59.93 | 39.92 | 84.67 | 54.32 | 49.04 | 80.39 | 31.16 | 72.94 | | [sentence-t5-xxl](https://huggingface.co/sentence-transformers/sentence-t5-xxl) | 9.73 | 768 | 512 | 59.51 | 43.72 | 85.06 | 56.42 | 42.24 | 82.63 | 30.08 | 73.42 | | [all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) | 0.44 | 768 | 514 | 57.78 | 43.69 | 83.04 | 59.36 | 43.81 | 80.28 | 27.49 | 65.07 | | [sgpt-bloom-7b1-msmarco](https://huggingface.co/bigscience/sgpt-bloom-7b1-msmarco) | 28.27 | 4096 | 2048 | 57.59 | 38.93 | 81.9 | 55.65 | 48.22 | 77.74 | 33.6 | 66.19 | | [all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) | 0.13 | 384 | 512 | 56.53 | 41.81 | 82.41 | 58.44 | 42.69 | 79.8 | 27.9 | 63.21 | | [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) | 0.09 | 384 | 512 | 56.26 | 42.35 | 82.37 | 58.04 | 41.95 | 78.9 | 30.81 | 63.05 | | [contriever-base-msmarco](https://huggingface.co/nthakur/contriever-base-msmarco) | 0.44 | 768 | 512 | 56.00 | 41.1 | 82.54 | 53.14 | 41.88 | 76.51 | 30.36 | 66.68 | | [sentence-t5-base](https://huggingface.co/sentence-transformers/sentence-t5-base) | 0.22 | 768 | 512 | 55.27 | 40.21 | 85.18 | 53.09 | 33.63 | 81.14 | 31.39 | 69.81 | ## Usage This model can be used with both [Python](#python) and [JavaScript](#javascript). ### Python Use with [Transformers](https://huggingface.co/docs/transformers/index) and [PyTorch](https://pytorch.org/docs/stable/index.html): ```python import torch.nn.functional as F from torch import Tensor from transformers import AutoTokenizer, AutoModel def average_pool(last_hidden_states: Tensor, attention_mask: Tensor) -> Tensor: last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0) return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None] input_texts = [ "what is the capital of China?", "how to implement quick sort in python?", "Beijing", "sorting algorithms" ] tokenizer = AutoTokenizer.from_pretrained("Supabase/gte-small") model = AutoModel.from_pretrained("Supabase/gte-small") # Tokenize the input texts batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt') outputs = model(**batch_dict) embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask']) # (Optionally) normalize embeddings embeddings = F.normalize(embeddings, p=2, dim=1) scores = (embeddings[:1] @ embeddings[1:].T) * 100 print(scores.tolist()) ``` Use with [sentence-transformers](https://www.sbert.net/): ```python from sentence_transformers import SentenceTransformer from sentence_transformers.util import cos_sim sentences = ['That is a happy person', 'That is a very happy person'] model = SentenceTransformer('Supabase/gte-small') embeddings = model.encode(sentences) print(cos_sim(embeddings[0], embeddings[1])) ``` ### JavaScript This model can be used with JavaScript via [Transformers.js](https://huggingface.co/docs/transformers.js/index). Use with [Deno](https://deno.land/manual/introduction) or [Supabase Edge Functions](https://supabase.com/docs/guides/functions): ```ts import { serve } from 'https://deno.land/std@0.168.0/http/server.ts' import { env, pipeline } from 'https://cdn.jsdelivr.net/npm/@xenova/transformers@2.5.0' // Configuration for Deno runtime env.useBrowserCache = false; env.allowLocalModels = false; const pipe = await pipeline( 'feature-extraction', 'Supabase/gte-small', ); serve(async (req) => { // Extract input string from JSON body const { input } = await req.json(); // Generate the embedding from the user input const output = await pipe(input, { pooling: 'mean', normalize: true, }); // Extract the embedding output const embedding = Array.from(output.data); // Return the embedding return new Response( JSON.stringify({ embedding }), { headers: { 'Content-Type': 'application/json' } } ); }); ``` Use within the browser ([JavaScript Modules](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Modules)): ```html <script type="module"> import { pipeline } from 'https://cdn.jsdelivr.net/npm/@xenova/transformers@2.5.0'; const pipe = await pipeline( 'feature-extraction', 'Supabase/gte-small', ); // Generate the embedding from text const output = await pipe('Hello world', { pooling: 'mean', normalize: true, }); // Extract the embedding output const embedding = Array.from(output.data); console.log(embedding); </script> ``` Use within [Node.js](https://nodejs.org/en/docs) or a web bundler ([Webpack](https://webpack.js.org/concepts/), etc): ```js import { pipeline } from '@xenova/transformers'; const pipe = await pipeline( 'feature-extraction', 'Supabase/gte-small', ); // Generate the embedding from text const output = await pipe('Hello world', { pooling: 'mean', normalize: true, }); // Extract the embedding output const embedding = Array.from(output.data); console.log(embedding); ``` ### Limitation This model exclusively caters to English texts, and any lengthy texts will be truncated to a maximum of 512 tokens.

Helsinki-NLP/opus-mt-ru-en

Helsinki-NLP

transformers

translation

--- tags: - translation license: cc-by-4.0 --- ### opus-mt-ru-en ## Table of Contents - [Model Details](#model-details) - [Uses](#uses) - [Risks, Limitations and Biases](#risks-limitations-and-biases) - [Training](#training) - [Evaluation](#evaluation) - [Citation Information](#citation-information) - [How to Get Started With the Model](#how-to-get-started-with-the-model) ## Model Details **Model Description:** - **Developed by:** Language Technology Research Group at the University of Helsinki - **Model Type:** Transformer-align - **Language(s):** - Source Language: Russian - Target Language: English - **License:** CC-BY-4.0 - **Resources for more information:** - [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train) ## Uses #### Direct Use This model can be used for translation and text-to-text generation. ## Risks, Limitations and Biases **CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes.** Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Further details about the dataset for this model can be found in the OPUS readme: [ru-en](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/ru-en/README.md) ## Training #### Training Data ##### Preprocessing * Pre-processing: Normalization + SentencePiece * Dataset: [opus](https://github.com/Helsinki-NLP/Opus-MT) * Download original weights: [opus-2020-02-26.zip](https://object.pouta.csc.fi/OPUS-MT-models/ru-en/opus-2020-02-26.zip) * Test set translations: [opus-2020-02-26.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/ru-en/opus-2020-02-26.test.txt) ## Evaluation #### Results * test set scores: [opus-2020-02-26.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/ru-en/opus-2020-02-26.eval.txt) #### Benchmarks | testset | BLEU | chr-F | |-----------------------|-------|-------| | newstest2012.ru.en | 34.8 | 0.603 | | newstest2013.ru.en | 27.9 | 0.545 | | newstest2014-ruen.ru.en | 31.9 | 0.591 | | newstest2015-enru.ru.en | 30.4 | 0.568 | | newstest2016-enru.ru.en | 30.1 | 0.565 | | newstest2017-enru.ru.en | 33.4 | 0.593 | | newstest2018-enru.ru.en | 29.6 | 0.565 | | newstest2019-ruen.ru.en | 31.4 | 0.576 | | Tatoeba.ru.en | 61.1 | 0.736 | ## Citation Information ```bibtex @InProceedings{TiedemannThottingal:EAMT2020, author = {J{\"o}rg Tiedemann and Santhosh Thottingal}, title = {{OPUS-MT} — {B}uilding open translation services for the {W}orld}, booktitle = {Proceedings of the 22nd Annual Conferenec of the European Association for Machine Translation (EAMT)}, year = {2020}, address = {Lisbon, Portugal} } ``` ## How to Get Started With the Model ```python from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-ru-en") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-ru-en") ```

microsoft/table-transformer-structure-recognition-v1.1-all

microsoft

transformers

object-detection

--- license: mit --- # Table Transformer (pre-trained for Table Structure Recognition) Table Transformer (TATR) model trained on PubTables1M and FinTabNet.c. It was introduced in the paper [Aligning benchmark datasets for table structure recognition](https://arxiv.org/abs/2303.00716) by Smock et al. and first released in [this repository](https://github.com/microsoft/table-transformer). Disclaimer: The team releasing Table Transformer did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description The Table Transformer is equivalent to [DETR](https://huggingface.co/docs/transformers/model_doc/detr), a Transformer-based object detection model. Note that the authors decided to use the "normalize before" setting of DETR, which means that layernorm is applied before self- and cross-attention. ## Usage You can use the raw model for detecting tables in documents. See the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/table-transformer) for more info.

Helsinki-NLP/opus-mt-de-en

Helsinki-NLP

transformers

translation

--- tags: - translation license: apache-2.0 --- ### opus-mt-de-en * source languages: de * target languages: en * OPUS readme: [de-en](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/de-en/README.md) * dataset: opus * model: transformer-align * pre-processing: normalization + SentencePiece * download original weights: [opus-2020-02-26.zip](https://object.pouta.csc.fi/OPUS-MT-models/de-en/opus-2020-02-26.zip) * test set translations: [opus-2020-02-26.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-en/opus-2020-02-26.test.txt) * test set scores: [opus-2020-02-26.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-en/opus-2020-02-26.eval.txt) ## Benchmarks | testset | BLEU | chr-F | |-----------------------|-------|-------| | newssyscomb2009.de.en | 29.4 | 0.557 | | news-test2008.de.en | 27.8 | 0.548 | | newstest2009.de.en | 26.8 | 0.543 | | newstest2010.de.en | 30.2 | 0.584 | | newstest2011.de.en | 27.4 | 0.556 | | newstest2012.de.en | 29.1 | 0.569 | | newstest2013.de.en | 32.1 | 0.583 | | newstest2014-deen.de.en | 34.0 | 0.600 | | newstest2015-ende.de.en | 34.2 | 0.599 | | newstest2016-ende.de.en | 40.4 | 0.649 | | newstest2017-ende.de.en | 35.7 | 0.610 | | newstest2018-ende.de.en | 43.7 | 0.667 | | newstest2019-deen.de.en | 40.1 | 0.642 | | Tatoeba.de.en | 55.4 | 0.707 |

mlabonne/NeuralDaredevil-7B

mlabonne

transformers

text-generation

--- license: cc-by-nc-4.0 tags: - merge - mergekit - lazymergekit - dpo - rlhf - mlabonne/example base_model: mlabonne/Daredevil-7B model-index: - name: NeuralDaredevil-7B results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 69.88 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDaredevil-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 87.62 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDaredevil-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 65.12 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDaredevil-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 66.85 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDaredevil-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 82.08 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDaredevil-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 73.16 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDaredevil-7B name: Open LLM Leaderboard ---  # NeuralDaredevil-7B NeuralDaredevil-7B is a DPO fine-tune of [mlabonne/Daredevil-7B](https://huggingface.co/mlabonne/Daredevil-7B) using the [argilla/distilabel-intel-orca-dpo-pairs](https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs) preference dataset and my DPO notebook from [this article](https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac). Thanks [Argilla](https://huggingface.co/argilla) for providing the dataset and the training recipe [here](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp). 💪 ## 🏆 Evaluation ### Nous The evaluation was performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval) on Nous suite. | Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench | |---|---:|---:|---:|---:|---:| | [**mlabonne/NeuralDaredevil-7B**](https://huggingface.co/mlabonne/NeuralDaredevil-7B) [📄](https://gist.github.com/mlabonne/cbeb077d1df71cb81c78f742f19f4155) | **59.39** | **45.23** | **76.2** | **67.61** | **48.52** | | [mlabonne/Beagle14-7B](https://huggingface.co/mlabonne/Beagle14-7B) [📄](https://gist.github.com/mlabonne/f5a5bf8c0827bbec2f05b97cc62d642c) | 59.4 | 44.38 | 76.53 | 69.44 | 47.25 | | [argilla/distilabeled-Marcoro14-7B-slerp](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp) [📄](https://gist.github.com/mlabonne/9082c4e59f4d3f3543c5eda3f4807040) | 58.93 | 45.38 | 76.48 | 65.68 | 48.18 | | [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) [📄](https://gist.github.com/mlabonne/b31572a4711c945a4827e7242cfc4b9d) | 58.4 | 44.59 | 76.17 | 65.94 | 46.9 | | [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) [📄](https://gist.github.com/mlabonne/1afab87b543b0717ec08722cf086dcc3) | 53.71 | 44.17 | 73.72 | 52.53 | 44.4 | | [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) [📄](https://gist.github.com/mlabonne/88b21dd9698ffed75d6163ebdc2f6cc8) | 52.42 | 42.75 | 72.99 | 52.99 | 40.94 | You can find the complete benchmark on [YALL - Yet Another LLM Leaderboard](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard). # [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_mlabonne__NeuralDaredevil-7B) | Metric |Value| |---------------------------------|----:| |Avg. |74.12| |AI2 Reasoning Challenge (25-Shot)|69.88| |HellaSwag (10-Shot) |87.62| |MMLU (5-Shot) |65.12| |TruthfulQA (0-shot) |66.85| |Winogrande (5-shot) |82.08| |GSM8k (5-shot) |73.16| ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "mlabonne/NeuralDaredevil-7B" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ``` <p align="center"> <a href="https://github.com/argilla-io/distilabel"> <img src="https://raw.githubusercontent.com/argilla-io/distilabel/main/docs/assets/distilabel-badge-light.png" alt="Built with Distilabel" width="200" height="32"/> </a> </p>

microsoft/codebert-base

microsoft

transformers

feature-extraction

## CodeBERT-base Pretrained weights for [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://arxiv.org/abs/2002.08155). ### Training Data The model is trained on bi-modal data (documents & code) of [CodeSearchNet](https://github.com/github/CodeSearchNet) ### Training Objective This model is initialized with Roberta-base and trained with MLM+RTD objective (cf. the paper). ### Usage Please see [the official repository](https://github.com/microsoft/CodeBERT) for scripts that support "code search" and "code-to-document generation". ### Reference 1. [CodeBERT trained with Masked LM objective](https://huggingface.co/microsoft/codebert-base-mlm) (suitable for code completion) 2. 🤗 [Hugging Face's CodeBERTa](https://huggingface.co/huggingface/CodeBERTa-small-v1) (small size, 6 layers) ### Citation ```bibtex @misc{feng2020codebert, title={CodeBERT: A Pre-Trained Model for Programming and Natural Languages}, author={Zhangyin Feng and Daya Guo and Duyu Tang and Nan Duan and Xiaocheng Feng and Ming Gong and Linjun Shou and Bing Qin and Ting Liu and Daxin Jiang and Ming Zhou}, year={2020}, eprint={2002.08155}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

Helsinki-NLP/opus-mt-en-fr

Helsinki-NLP

transformers

translation

--- pipeline_tag: translation license: apache-2.0 --- ### opus-mt-en-fr * source languages: en * target languages: fr * OPUS readme: [en-fr](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-fr/README.md) * dataset: opus * model: transformer-align * pre-processing: normalization + SentencePiece * download original weights: [opus-2020-02-26.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-fr/opus-2020-02-26.zip) * test set translations: [opus-2020-02-26.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-fr/opus-2020-02-26.test.txt) * test set scores: [opus-2020-02-26.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-fr/opus-2020-02-26.eval.txt) ## Benchmarks | testset | BLEU | chr-F | |-----------------------|-------|-------| | newsdiscussdev2015-enfr.en.fr | 33.8 | 0.602 | | newsdiscusstest2015-enfr.en.fr | 40.0 | 0.643 | | newssyscomb2009.en.fr | 29.8 | 0.584 | | news-test2008.en.fr | 27.5 | 0.554 | | newstest2009.en.fr | 29.4 | 0.577 | | newstest2010.en.fr | 32.7 | 0.596 | | newstest2011.en.fr | 34.3 | 0.611 | | newstest2012.en.fr | 31.8 | 0.592 | | newstest2013.en.fr | 33.2 | 0.589 | | Tatoeba.en.fr | 50.5 | 0.672 |

hustvl/vitmatte-small-composition-1k

hustvl

transformers

--- license: apache-2.0 tags: - vision --- # ViTMatte model ViTMatte model trained on Composition-1k. It was introduced in the paper [ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers](https://arxiv.org/abs/2305.15272) by Yao et al. and first released in [this repository](https://github.com/hustvl/ViTMatte). Disclaimer: The team releasing ViTMatte did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description ViTMatte is a simple approach to image matting, the task of accurately estimating the foreground object in an image. The model consists of a Vision Transformer (ViT) with a lightweight head on top. <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/vitmatte_architecture.png" alt="drawing" width="600"/> <small> ViTMatte high-level overview. Taken from the <a href="https://arxiv.org/abs/2305.15272">original paper.</a> </small> ## Intended uses & limitations You can use the raw model for image matting. See the [model hub](https://huggingface.co/models?search=vitmatte) to look for other fine-tuned versions that may interest you. ### How to use We refer to the [docs](https://huggingface.co/docs/transformers/main/en/model_doc/vitmatte#transformers.VitMatteForImageMatting.forward.example). ### BibTeX entry and citation info ```bibtex @misc{yao2023vitmatte, title={ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers}, author={Jingfeng Yao and Xinggang Wang and Shusheng Yang and Baoyuan Wang}, year={2023}, eprint={2305.15272}, archivePrefix={arXiv}, primaryClass={cs.CV} } ```

google/byt5-small

google

transformers

text2text-generation

--- language: - multilingual - af - am - ar - az - be - bg - bn - ca - ceb - co - cs - cy - da - de - el - en - eo - es - et - eu - fa - fi - fil - fr - fy - ga - gd - gl - gu - ha - haw - hi - hmn - ht - hu - hy - ig - is - it - iw - ja - jv - ka - kk - km - kn - ko - ku - ky - la - lb - lo - lt - lv - mg - mi - mk - ml - mn - mr - ms - mt - my - ne - nl - no - ny - pa - pl - ps - pt - ro - ru - sd - si - sk - sl - sm - sn - so - sq - sr - st - su - sv - sw - ta - te - tg - th - tr - uk - und - ur - uz - vi - xh - yi - yo - zh - zu datasets: - mc4 license: apache-2.0 --- # ByT5 - Small ByT5 is a tokenizer-free version of [Google's T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) and generally follows the architecture of [MT5](https://huggingface.co/google/mt5-small). ByT5 was only pre-trained on [mC4](https://www.tensorflow.org/datasets/catalog/c4#c4multilingual) excluding any supervised training with an average span-mask of 20 UTF-8 characters. Therefore, this model has to be fine-tuned before it is useable on a downstream task. ByT5 works especially well on noisy text data,*e.g.*, `google/byt5-small` significantly outperforms [mt5-small](https://huggingface.co/google/mt5-small) on [TweetQA](https://arxiv.org/abs/1907.06292). Paper: [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://arxiv.org/abs/2105.13626) Authors: *Linting Xue, Aditya Barua, Noah Constant, Rami Al-Rfou, Sharan Narang, Mihir Kale, Adam Roberts, Colin Raffel* ## Example Inference ByT5 works on raw UTF-8 bytes and can be used without a tokenizer: ```python from transformers import T5ForConditionalGeneration import torch model = T5ForConditionalGeneration.from_pretrained('google/byt5-small') input_ids = torch.tensor([list("Life is like a box of chocolates.".encode("utf-8"))]) + 3 # add 3 for special tokens labels = torch.tensor([list("La vie est comme une boîte de chocolat.".encode("utf-8"))]) + 3 # add 3 for special tokens loss = model(input_ids, labels=labels).loss # forward pass ``` For batched inference & training it is however recommended using a tokenizer class for padding: ```python from transformers import T5ForConditionalGeneration, AutoTokenizer model = T5ForConditionalGeneration.from_pretrained('google/byt5-small') tokenizer = AutoTokenizer.from_pretrained('google/byt5-small') model_inputs = tokenizer(["Life is like a box of chocolates.", "Today is Monday."], padding="longest", return_tensors="pt") labels = tokenizer(["La vie est comme une boîte de chocolat.", "Aujourd'hui c'est lundi."], padding="longest", return_tensors="pt").input_ids loss = model(**model_inputs, labels=labels).loss # forward pass ``` ## Abstract Most widely-used pre-trained language models operate on sequences of tokens corresponding to word or subword units. Encoding text as a sequence of tokens requires a tokenizer, which is typically created as an independent artifact from the model. Token-free models that instead operate directly on raw text (bytes or characters) have many benefits: they can process text in any language out of the box, they are more robust to noise, and they minimize technical debt by removing complex and error-prone text preprocessing pipelines. Since byte or character sequences are longer than token sequences, past work on token-free models has often introduced new model architectures designed to amortize the cost of operating directly on raw text. In this paper, we show that a standard Transformer architecture can be used with minimal modifications to process byte sequences. We carefully characterize the trade-offs in terms of parameter count, training FLOPs, and inference speed, and show that byte-level models are competitive with their token-level counterparts. We also demonstrate that byte-level models are significantly more robust to noise and perform better on tasks that are sensitive to spelling and pronunciation. As part of our contribution, we release a new set of pre-trained byte-level Transformer models based on the T5 architecture, as well as all code and data used in our experiments. 

sentence-transformers/distilbert-base-nli-stsb-mean-tokens

sentence-transformers

sentence-transformers

sentence-similarity

--- license: apache-2.0 library_name: sentence-transformers tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers pipeline_tag: sentence-similarity --- **⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)** # sentence-transformers/distilbert-base-nli-stsb-mean-tokens This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('sentence-transformers/distilbert-base-nli-stsb-mean-tokens') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/distilbert-base-nli-stsb-mean-tokens') model = AutoModel.from_pretrained('sentence-transformers/distilbert-base-nli-stsb-mean-tokens') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(**encoded_input) # Perform pooling. In this case, max pooling. sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/distilbert-base-nli-stsb-mean-tokens) ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False}) ) ``` ## Citing & Authors This model was trained by [sentence-transformers](https://www.sbert.net/). If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084): ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "http://arxiv.org/abs/1908.10084", } ```

microsoft/Phi-3-medium-128k-instruct

microsoft

transformers

text-generation

--- license: mit license_link: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE language: - multilingual pipeline_tag: text-generation tags: - nlp - code inference: parameters: temperature: 0.7 widget: - messages: - role: user content: Can you provide ways to eat combinations of bananas and dragonfruits? --- ## Model Summary The Phi-3-Medium-128K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Phi-3 family with the Medium version in two variants [4k](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct) and [128K](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) which is the context length (in tokens) that it can support. The model has underwent a post-training process that incorporates both supervised fine-tuning and direct preference optimization for the instruction following and safety measures. When assessed against benchmarks testing common sense, language understanding, math, code, long context and logical reasoning, Phi-3-Medium-128K-Instruct showcased a robust and state-of-the-art performance among models of the same-size and next-size-up. Resources and Technical Documentation: + [Phi-3 Microsoft Blog](https://aka.ms/Phi-3Build2024) + [Phi-3 Technical Report](https://aka.ms/phi3-tech-report) + [Phi-3 on Azure AI Studio](https://aka.ms/phi3-azure-ai) + [Phi-3 Cookbook](https://github.com/microsoft/Phi-3CookBook) | | Short Context | Long Context | | ------- | ------------- | ------------ | | Mini | 4K [[HF]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-onnx) ; [[GGUF]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct-onnx)| | Small | 8K [[HF]](https://huggingface.co/microsoft/Phi-3-small-8k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-small-8k-instruct-onnx-cuda) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-small-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-small-128k-instruct-onnx-cuda)| | Medium | 4K [[HF]](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct-onnx-cuda) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct-onnx-cuda)| | Vision | | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct-onnx-cuda)| ## Intended Uses **Primary use cases** The model is intended for broad commercial and research use in English. The model provides uses for general purpose AI systems and applications which require : 1) Memory/compute constrained environments 2) Latency bound scenarios 3) Strong reasoning (especially code, math and logic) Our model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features. **Use case considerations** Our models are not specifically designed or evaluated for all downstream purposes. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fariness before using within a specific downstream use case, particularly for high risk scenarios. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case. Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under. ## How to Use Phi-3-Medium-128k-Instruct has been integrated in the development version (4.40.2) of `transformers`. Until the official version is released through `pip`, ensure that you are doing one of the following: * When loading the model, ensure that `trust_remote_code=True` is passed as an argument of the `from_pretrained()` function. * Update your local `transformers` to the development version: `pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers`. The previous command is an alternative to cloning and installing from the source. The current `transformers` version can be verified with: `pip list | grep transformers`. Phi-3-Medium-128k-Instruct is also available in [Azure AI Studio](https://aka.ms/phi3-azure-ai). ### Tokenizer Phi-3-Medium-128k-Instruct supports a vocabulary size of up to `32064` tokens. The [tokenizer files](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/blob/main/added_tokens.json) already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size. ### Chat Format Given the nature of the training data, the Phi-3-Medium-128k-Instruct model is best suited for prompts using the chat format as follows. You can provide the prompt as a question with a generic template as follow: ```markdown <|user|>\nQuestion <|end|>\n<|assistant|> ``` For example: ```markdown <|user|> How to explain Internet for a medieval knight?<|end|> <|assistant|> ``` where the model generates the text after `<|assistant|>` . In case of few-shots prompt, the prompt can be formatted as the following: ```markdown <|user|> I am going to Paris, what should I see?<|end|> <|assistant|> Paris, the capital of France, is known for its stunning architecture, art museums, historical landmarks, and romantic atmosphere. Here are some of the top attractions to see in Paris:\n\n1. The Eiffel Tower: The iconic Eiffel Tower is one of the most recognizable landmarks in the world and offers breathtaking views of the city.\n2. The Louvre Museum: The Louvre is one of the world's largest and most famous museums, housing an impressive collection of art and artifacts, including the Mona Lisa.\n3. Notre-Dame Cathedral: This beautiful cathedral is one of the most famous landmarks in Paris and is known for its Gothic architecture and stunning stained glass windows.\n\nThese are just a few of the many attractions that Paris has to offer. With so much to see and do, it's no wonder that Paris is one of the most popular tourist destinations in the world."<|end|> <|user|> What is so great about #1?<|end|> <|assistant|> ``` ### Sample inference code This code snippets show how to get quickly started with running the model on a GPU: ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline torch.random.manual_seed(0) model_id = "microsoft/Phi-3-medium-128k-instruct" model = AutoModelForCausalLM.from_pretrained( model_id, device_map="cuda", torch_dtype="auto", trust_remote_code=True, ) tokenizer = AutoTokenizer.from_pretrained(model_id) messages = [ {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"}, {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."}, {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"}, ] pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, ) generation_args = { "max_new_tokens": 500, "return_full_text": False, "temperature": 0.0, "do_sample": False, } output = pipe(messages, **generation_args) print(output[0]['generated_text']) ``` *Some applications/frameworks might not include a BOS token (`<s>`) at the start of the conversation. Please ensure that it is included since it provides more reliable results.* ## Responsible AI Considerations Like other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include: + Quality of Service: the Phi models are trained primarily on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English. + Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases. + Inappropriate or Offensive Content: these models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case. + Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated. + Limited Scope for Code: Majority of Phi-3 training data is based in Python and use common packages such as "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses. Developers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include: + Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques. + High-Risk Scenarios: Developers should assess suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context. + Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG). + Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case. + Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations. ## Training ### Model * Architecture: Phi-3-Medium-128k-Instruct has 14B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines. * Inputs: Text. It is best suited for prompts using chat format. * Context length: 128k tokens * GPUs: 512 H100-80G * Training time: 42 days * Training data: 4.8T tokens * Outputs: Generated text in response to the input * Dates: Our models were trained between February and April 2024 * Status: This is a static model trained on an offline dataset with cutoff date October 2023. Future versions of the tuned models may be released as we improve models. * Release dates: The model weight is released on May 21, 2024. ### Datasets Our training data includes a wide variety of sources, totaling 4.8 trillion tokens (including 10% multilingual), and is a combination of 1) Publicly available documents filtered rigorously for quality, selected high-quality educational data, and code; 2) Newly created synthetic, “textbook-like” data for the purpose of teaching math, coding, common sense reasoning, general knowledge of the world (science, daily activities, theory of mind, etc.); 3) High quality chat format supervised data covering various topics to reflect human preferences on different aspects such as instruct-following, truthfulness, honesty and helpfulness. We are focusing on the quality of data that could potentially improve the reasoning ability for the model, and we filter the publicly available documents to contain the correct level of knowledge. As an example, the result of a game in premier league in a particular day might be good training data for frontier models, but we need to remove such information to leave more model capacity for reasoning for the small size models. More details about data can be found in the [Phi-3 Technical Report](https://aka.ms/phi3-tech-report). ## Benchmarks We report the results for Phi-3-Medium-128k-Instruct on standard open-source benchmarks measuring the model's reasoning ability (both common sense reasoning and logical reasoning). We compare to Mixtral-8x22b, Gemini-Pro, Command R+ 104B, Llama-3-70B-Instruct, GPT-3.5-Turbo-1106, and GPT-4-Turbo-1106(Chat). All the reported numbers are produced with the exact same pipeline to ensure that the numbers are comparable. These numbers might differ from other published numbers due to slightly different choices in the evaluation. As is now standard, we use few-shot prompts to evaluate the models, at temperature 0. The prompts and number of shots are part of a Microsoft internal tool to evaluate language models, and in particular we did no optimization to the pipeline for Phi-3. More specifically, we do not change prompts, pick different few-shot examples, change prompt format, or do any other form of optimization for the model. The number of k–shot examples is listed per-benchmark. |Benchmark|Phi-3-Medium-128k-Instruct<br>14b|Command R+<br>104B|Mixtral<br>8x22B|Llama-3-70B-Instruct|GPT3.5-Turbo<br>version 1106|Gemini<br>Pro|GPT-4-Turbo<br>version 1106 (Chat)| |---------|-----------------------|--------|-------------|-------------------|-------------------|----------|------------------------| |AGI Eval<br>5-shot|49.7|50.1|54.0|56.9|48.4|49.0|59.6| |MMLU<br>5-shot|76.6|73.8|76.2|80.2|71.4|66.7|84.0| |BigBench Hard<br>3-shot|77.9|74.1|81.8|80.4|68.3|75.6|87.7| |ANLI<br>7-shot|57.3|63.4|65.2|68.3|58.1|64.2|71.7| |HellaSwag<br>5-shot|81.6|78.0|79.0|82.6|78.8|76.2|88.3| |ARC Challenge<br>10-shot|91.0|86.9|91.3|93.0|87.4|88.3|95.6| |ARC Easy<br>10-shot|97.6|95.7|96.9|98.2|96.3|96.1|98.8| |BoolQ<br>2-shot|86.5|86.1|82.7|89.1|79.1|86.4|91.3| |CommonsenseQA<br>10-shot|82.2|82.0|82.0|84.4|79.6|81.8|86.7| |MedQA<br>2-shot|67.6|59.2|67.9|78.5|63.4|58.2|83.7| |OpenBookQA<br>10-shot|87.2|86.8|88.6|91.8|86.0|86.4|93.4| |PIQA<br>5-shot|87.8|86.4|85.0|85.3|86.6|86.2|90.1| |Social IQA<br>5-shot|79.0|75.3|78.2|81.1|68.3|75.4|81.7| |TruthfulQA (MC2)<br>10-shot|74.3|57.8|67.4|81.9|67.7|72.6|85.2| |WinoGrande<br>5-shot|78.9|77.0|75.3|83.3|68.8|72.2|86.7| |TriviaQA<br>5-shot|73.9|82.8|84.5|78.5|85.8|80.2|73.3| |GSM8K Chain of Thought<br>8-shot|87.5|78.3|83.8|93.5|78.1|80.4|94.2| |HumanEval<br>0-shot|58.5|61.6|39.6|78.7|62.2|64.4|79.9| |MBPP<br>3-shot|73.8|68.9|70.7|81.3|77.8|73.2|86.7| |Average|77.3|75.0|76.3|82.5|74.3|75.4|85.2| We take a closer look at different categories across 80 public benchmark datasets at the table below: |Benchmark|Phi-3-Medium-128k-Instruct<br>14b|Command R+<br>104B|Mixtral<br>8x22B|Llama-3-70B-Instruct|GPT3.5-Turbo<br>version 1106|Gemini<br>Pro|GPT-4-Turbo<br>version 1106 (Chat)| |--------|------------------------|--------|-------------|-------------------|-------------------|----------|------------------------| | Popular aggregated benchmark | 72.3 | 69.9 | 73.4 | 76.3 | 67.0 | 67.5 | 80.5 | | Reasoning | 83.2 | 79.3 | 81.5 | 86.7 | 78.3 | 80.4 | 89.3 | | Language understanding | 75.3 | 75.7 | 78.7 | 77.9 | 70.4 | 75.3 | 81.6 | | Code generation | 64.2 | 68.6 | 60.0 | 69.3 | 70.4 | 66.7 | 76.1 | | Math | 52.9 | 45.3 | 52.5 | 59.7 | 52.8 | 50.9 | 67.1 | | Factual knowledge | 47.5 | 60.3 | 60.6 | 52.4 | 63.4 | 54.6 | 45.9 | | Multilingual | 62.2 | 67.8 | 69.8 | 62.0 | 67.0 | 73.4 | 78.2 | | Robustness | 70.2 | 57.9 | 65.5 | 78.7 | 69.3 | 69.7 | 84.6 | ## Software * [PyTorch](https://github.com/pytorch/pytorch) * [DeepSpeed](https://github.com/microsoft/DeepSpeed) * [Transformers](https://github.com/huggingface/transformers) * [Flash-Attention](https://github.com/HazyResearch/flash-attention) ## Hardware Note that by default, the Phi-3-Medium model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types: * NVIDIA A100 * NVIDIA A6000 * NVIDIA H100 If you want to run the model on: + Optimized inference on GPU, CPU, and Mobile: use the **ONNX** models [128k](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct-onnx-cuda) ## Cross Platform Support ONNX runtime ecosystem now supports Phi3 Medium models across platforms and hardware. Optimized phi-3 models are also published here in ONNX format, to run with ONNX Runtime on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets. DirectML GPU acceleration is supported for Windows desktops GPUs (AMD, Intel, and NVIDIA). Along with DML, ONNX Runtime provides cross platform support for Phi3 Medium across a range of devices CPU, GPU, and mobile. Here are some of the optimized configurations we have added: 1. ONNX models for int4 DML: Quantized to int4 via AWQ 2. ONNX model for fp16 CUDA 3. ONNX model for int4 CUDA: Quantized to int4 via RTN 4. ONNX model for int4 CPU and Mobile: Quantized to int4 via RTN ## License The model is licensed under the [MIT license](https://huggingface.co/microsoft/Phi-3-medium-128k/resolve/main/LICENSE). ## Trademarks This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.

sentence-transformers/all-distilroberta-v1

sentence-transformers

sentence-transformers

sentence-similarity

--- language: en license: apache-2.0 library_name: sentence-transformers tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers datasets: - s2orc - flax-sentence-embeddings/stackexchange_xml - ms_marco - gooaq - yahoo_answers_topics - code_search_net - search_qa - eli5 - snli - multi_nli - wikihow - natural_questions - trivia_qa - embedding-data/sentence-compression - embedding-data/flickr30k-captions - embedding-data/altlex - embedding-data/simple-wiki - embedding-data/QQP - embedding-data/SPECTER - embedding-data/PAQ_pairs - embedding-data/WikiAnswers pipeline_tag: sentence-similarity --- # all-distilroberta-v1 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('sentence-transformers/all-distilroberta-v1') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch import torch.nn.functional as F #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-distilroberta-v1') model = AutoModel.from_pretrained('sentence-transformers/all-distilroberta-v1') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(**encoded_input) # Perform pooling sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) # Normalize embeddings sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/all-distilroberta-v1) ------ ## Background The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective. We used the pretrained [`distilroberta-base`](https://huggingface.co/distilroberta-base) model and fine-tuned in on a 1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset. We developped this model during the [Community week using JAX/Flax for NLP & CV](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104), organized by Hugging Face. We developped this model as part of the project: [Train the Best Sentence Embedding Model Ever with 1B Training Pairs](https://discuss.huggingface.co/t/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs/7354). We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks. ## Intended uses Our model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks. By default, input text longer than 128 word pieces is truncated. ## Training procedure ### Pre-training We use the pretrained [`distilroberta-base`](https://huggingface.co/distilroberta-base). Please refer to the model card for more detailed information about the pre-training procedure. ### Fine-tuning We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch. We then apply the cross entropy loss by comparing with true pairs. #### Hyper parameters We trained ou model on a TPU v3-8. We train the model during 920k steps using a batch size of 512 (64 per TPU core). We use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with a 2e-5 learning rate. The full training script is accessible in this current repository: `train_script.py`. #### Training data We use the concatenation from multiple datasets to fine-tune our model. The total number of sentence pairs is above 1 billion sentences. We sampled each dataset given a weighted probability which configuration is detailed in the `data_config.json` file. | Dataset | Paper | Number of training tuples | |--------------------------------------------------------|:----------------------------------------:|:--------------------------:| | [Reddit comments (2015-2018)](https://github.com/PolyAI-LDN/conversational-datasets/tree/master/reddit) | [paper](https://arxiv.org/abs/1904.06472) | 726,484,430 | | [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Abstracts) | [paper](https://aclanthology.org/2020.acl-main.447/) | 116,288,806 | | [WikiAnswers](https://github.com/afader/oqa#wikianswers-corpus) Duplicate question pairs | [paper](https://doi.org/10.1145/2623330.2623677) | 77,427,422 | | [PAQ](https://github.com/facebookresearch/PAQ) (Question, Answer) pairs | [paper](https://arxiv.org/abs/2102.07033) | 64,371,441 | | [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Titles) | [paper](https://aclanthology.org/2020.acl-main.447/) | 52,603,982 | | [S2ORC](https://github.com/allenai/s2orc) (Title, Abstract) | [paper](https://aclanthology.org/2020.acl-main.447/) | 41,769,185 | | [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Body) pairs | - | 25,316,456 | | [MS MARCO](https://microsoft.github.io/msmarco/) triplets | [paper](https://doi.org/10.1145/3404835.3462804) | 9,144,553 | | [GOOAQ: Open Question Answering with Diverse Answer Types](https://github.com/allenai/gooaq) | [paper](https://arxiv.org/pdf/2104.08727.pdf) | 3,012,496 | | [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 1,198,260 | | [Code Search](https://huggingface.co/datasets/code_search_net) | - | 1,151,414 | | [COCO](https://cocodataset.org/#home) Image captions | [paper](https://link.springer.com/chapter/10.1007%2F978-3-319-10602-1_48) | 828,395| | [SPECTER](https://github.com/allenai/specter) citation triplets | [paper](https://doi.org/10.18653/v1/2020.acl-main.207) | 684,100 | | [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Question, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 681,164 | | [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Question) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 659,896 | | [SearchQA](https://huggingface.co/datasets/search_qa) | [paper](https://arxiv.org/abs/1704.05179) | 582,261 | | [Eli5](https://huggingface.co/datasets/eli5) | [paper](https://doi.org/10.18653/v1/p19-1346) | 325,475 | | [Flickr 30k](https://shannon.cs.illinois.edu/DenotationGraph/) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/229/33) | 317,695 | | [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles) | | 304,525 | | AllNLI ([SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) | [paper SNLI](https://doi.org/10.18653/v1/d15-1075), [paper MultiNLI](https://doi.org/10.18653/v1/n18-1101) | 277,230 | | [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (bodies) | | 250,519 | | [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles+bodies) | | 250,460 | | [Sentence Compression](https://github.com/google-research-datasets/sentence-compression) | [paper](https://www.aclweb.org/anthology/D13-1155/) | 180,000 | | [Wikihow](https://github.com/pvl/wikihow_pairs_dataset) | [paper](https://arxiv.org/abs/1810.09305) | 128,542 | | [Altlex](https://github.com/chridey/altlex/) | [paper](https://aclanthology.org/P16-1135.pdf) | 112,696 | | [Quora Question Triplets](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) | - | 103,663 | | [Simple Wikipedia](https://cs.pomona.edu/~dkauchak/simplification/) | [paper](https://www.aclweb.org/anthology/P11-2117/) | 102,225 | | [Natural Questions (NQ)](https://ai.google.com/research/NaturalQuestions) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/1455) | 100,231 | | [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/) | [paper](https://aclanthology.org/P18-2124.pdf) | 87,599 | | [TriviaQA](https://huggingface.co/datasets/trivia_qa) | - | 73,346 | | **Total** | | **1,124,818,467** |

unsloth/llama-3-8b-bnb-4bit

unsloth

transformers

text-generation

--- language: - en license: llama2 library_name: transformers tags: - unsloth - transformers - llama - llama-3 --- # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth! Directly quantized 4bit model with `bitsandbytes`. Built with Meta Llama 3 We have a Google Colab Tesla T4 notebook for Llama-3 8b here: https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk) [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy%20me%20a%20coffee%20button.png" width="200"/>](https://ko-fi.com/unsloth) [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) ## ✨ Finetune for Free All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face. | Unsloth supports | Free Notebooks | Performance | Memory use | |-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------| | **Llama-3 8b** | [▶️ Start on Colab](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing) | 2.4x faster | 58% less | | **Gemma 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing) | 2.4x faster | 58% less | | **Mistral 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less | | **Llama-2 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lBzz5KeZJKXjvivbYvmGarix9Ao6Wxe5?usp=sharing) | 2.2x faster | 43% less | | **TinyLlama** | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less | | **CodeLlama 34b** A100 | [▶️ Start on Colab](https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing) | 1.9x faster | 27% less | | **Mistral 7b** 1xT4 | [▶️ Start on Kaggle](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook) | 5x faster\* | 62% less | | **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less | - This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates. - This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr. - \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.

mistralai/Mixtral-8x7B-Instruct-v0.1

mistralai

transformers

text-generation

--- license: apache-2.0 language: - fr - it - de - es - en inference: parameters: temperature: 0.5 widget: - messages: - role: user content: What is your favorite condiment? --- # Model Card for Mixtral-8x7B ### > [!CAUTION] > ⚠️ > The `transformers` tokenizer might give incorrect results as it has not been tested by the Mistral team. To make sure that your encoding and decoding is correct, please use mistral-common as shown below: ```py from mistral_common.tokens.tokenizers.mistral import MistralTokenizer from mistral_common.protocol.instruct.messages import UserMessage from mistral_common.protocol.instruct.request import ChatCompletionRequest mistral_models_path = "MISTRAL_MODELS_PATH" tokenizer = MistralTokenizer.v1() completion_request = ChatCompletionRequest(messages=[UserMessage(content="Explain Machine Learning to me in a nutshell.")]) tokens = tokenizer.encode_chat_completion(completion_request).tokens ``` ## Inference with `mistral_inference` ```py from mistral_inference.model import Transformer from mistral_inference.generate import generate model = Transformer.from_folder(mistral_models_path) out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id) result = tokenizer.decode(out_tokens[0]) print(result) ``` ## Inference with hugging face `transformers` ```py from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1") model.to("cuda") generated_ids = model.generate(tokens, max_new_tokens=1000, do_sample=True) # decode with mistral tokenizer result = tokenizer.decode(generated_ids[0].tolist()) print(result) ``` > [!TIP] > PRs to correct the transformers tokenizer so that it gives 1-to-1 the same results as the mistral-common reference implementation are very welcome! --- The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested. For full details of this model please read our [release blog post](https://mistral.ai/news/mixtral-of-experts/). ## Warning This repo contains weights that are compatible with [vLLM](https://github.com/vllm-project/vllm) serving of the model as well as Hugging Face [transformers](https://github.com/huggingface/transformers) library. It is based on the original Mixtral [torrent release](magnet:?xt=urn:btih:5546272da9065eddeb6fcd7ffddeef5b75be79a7&dn=mixtral-8x7b-32kseqlen&tr=udp%3A%2F%http://2Fopentracker.i2p.rocks%3A6969%2Fannounce&tr=http%3A%2F%http://2Ftracker.openbittorrent.com%3A80%2Fannounce), but the file format and parameter names are different. Please note that model cannot (yet) be instantiated with HF. ## Instruction format This format must be strictly respected, otherwise the model will generate sub-optimal outputs. The template used to build a prompt for the Instruct model is defined as follows: ``` <s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST] ``` Note that `<s>` and `</s>` are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings. As reference, here is the pseudo-code used to tokenize instructions during fine-tuning: ```python def tokenize(text): return tok.encode(text, add_special_tokens=False) [BOS_ID] + tokenize("[INST]") + tokenize(USER_MESSAGE_1) + tokenize("[/INST]") + tokenize(BOT_MESSAGE_1) + [EOS_ID] + … tokenize("[INST]") + tokenize(USER_MESSAGE_N) + tokenize("[/INST]") + tokenize(BOT_MESSAGE_N) + [EOS_ID] ``` In the pseudo-code above, note that the `tokenize` method should not add a BOS or EOS token automatically, but should add a prefix space. In the Transformers library, one can use [chat templates](https://huggingface.co/docs/transformers/main/en/chat_templating) which make sure the right format is applied. ## Run the model ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto") messages = [ {"role": "user", "content": "What is your favourite condiment?"}, {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"}, {"role": "user", "content": "Do you have mayonnaise recipes?"} ] inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda") outputs = model.generate(inputs, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` By default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem: ### In half-precision Note `float16` precision only works on GPU devices <details> <summary> Click to expand </summary> ```diff + import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) + model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto") messages = [ {"role": "user", "content": "What is your favourite condiment?"}, {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"}, {"role": "user", "content": "Do you have mayonnaise recipes?"} ] input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda") outputs = model.generate(input_ids, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` </details> ### Lower precision using (8-bit & 4-bit) using `bitsandbytes` <details> <summary> Click to expand </summary> ```diff + import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) + model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, device_map="auto") text = "Hello my name is" messages = [ {"role": "user", "content": "What is your favourite condiment?"}, {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"}, {"role": "user", "content": "Do you have mayonnaise recipes?"} ] input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda") outputs = model.generate(input_ids, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` </details> ### Load the model with Flash Attention 2 <details> <summary> Click to expand </summary> ```diff + import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) + model = AutoModelForCausalLM.from_pretrained(model_id, use_flash_attention_2=True, device_map="auto") messages = [ {"role": "user", "content": "What is your favourite condiment?"}, {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"}, {"role": "user", "content": "Do you have mayonnaise recipes?"} ] input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda") outputs = model.generate(input_ids, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` </details> ## Limitations The Mixtral-8x7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs. # The Mistral AI Team Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.

sentence-transformers/stsb-roberta-base

sentence-transformers

sentence-transformers

sentence-similarity

--- license: apache-2.0 library_name: sentence-transformers tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers pipeline_tag: sentence-similarity --- **⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)** # sentence-transformers/stsb-roberta-base This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('sentence-transformers/stsb-roberta-base') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/stsb-roberta-base') model = AutoModel.from_pretrained('sentence-transformers/stsb-roberta-base') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(**encoded_input) # Perform pooling. In this case, max pooling. sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/stsb-roberta-base) ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': True}) with Transformer model: RobertaModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False}) ) ``` ## Citing & Authors This model was trained by [sentence-transformers](https://www.sbert.net/). If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084): ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "http://arxiv.org/abs/1908.10084", } ```

stabilityai/stable-diffusion-2-1

stabilityai

diffusers

text-to-image

--- license: openrail++ tags: - stable-diffusion - text-to-image pinned: true --- # Stable Diffusion v2-1 Model Card This model card focuses on the model associated with the Stable Diffusion v2-1 model, codebase available [here](https://github.com/Stability-AI/stablediffusion). This `stable-diffusion-2-1` model is fine-tuned from [stable-diffusion-2](https://huggingface.co/stabilityai/stable-diffusion-2) (`768-v-ema.ckpt`) with an additional 55k steps on the same dataset (with `punsafe=0.1`), and then fine-tuned for another 155k extra steps with `punsafe=0.98`. - Use it with the [`stablediffusion`](https://github.com/Stability-AI/stablediffusion) repository: download the `v2-1_768-ema-pruned.ckpt` [here](https://huggingface.co/stabilityai/stable-diffusion-2-1/blob/main/v2-1_768-ema-pruned.ckpt). - Use it with 🧨 [`diffusers`](#examples) ## Model Details - **Developed by:** Robin Rombach, Patrick Esser - **Model type:** Diffusion-based text-to-image generation model - **Language(s):** English - **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL) - **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses a fixed, pretrained text encoder ([OpenCLIP-ViT/H](https://github.com/mlfoundations/open_clip)). - **Resources for more information:** [GitHub Repository](https://github.com/Stability-AI/). - **Cite as:** @InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} } ## Examples Using the [🤗's Diffusers library](https://github.com/huggingface/diffusers) to run Stable Diffusion 2 in a simple and efficient manner. ```bash pip install diffusers transformers accelerate scipy safetensors ``` Running the pipeline (if you don't swap the scheduler it will run with the default DDIM, in this example we are swapping it to DPMSolverMultistepScheduler): ```python import torch from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler model_id = "stabilityai/stable-diffusion-2-1" # Use the DPMSolverMultistepScheduler (DPM-Solver++) scheduler here instead pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16) pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config) pipe = pipe.to("cuda") prompt = "a photo of an astronaut riding a horse on mars" image = pipe(prompt).images[0] image.save("astronaut_rides_horse.png") ``` **Notes**: - Despite not being a dependency, we highly recommend you to install [xformers](https://github.com/facebookresearch/xformers) for memory efficient attention (better performance) - If you have low GPU RAM available, make sure to add a `pipe.enable_attention_slicing()` after sending it to `cuda` for less VRAM usage (to the cost of speed) # Uses ## Direct Use The model is intended for research purposes only. Possible research areas and tasks include - Safe deployment of models which have the potential to generate harmful content. - Probing and understanding the limitations and biases of generative models. - Generation of artworks and use in design and other artistic processes. - Applications in educational or creative tools. - Research on generative models. Excluded uses are described below. ### Misuse, Malicious Use, and Out-of-Scope Use _Note: This section is originally taken from the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini), was used for Stable Diffusion v1, but applies in the same way to Stable Diffusion v2_. The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes. #### Out-of-Scope Use The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model. #### Misuse and Malicious Use Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to: - Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc. - Intentionally promoting or propagating discriminatory content or harmful stereotypes. - Impersonating individuals without their consent. - Sexual content without consent of the people who might see it. - Mis- and disinformation - Representations of egregious violence and gore - Sharing of copyrighted or licensed material in violation of its terms of use. - Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use. ## Limitations and Bias ### Limitations - The model does not achieve perfect photorealism - The model cannot render legible text - The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere” - Faces and people in general may not be generated properly. - The model was trained mainly with English captions and will not work as well in other languages. - The autoencoding part of the model is lossy - The model was trained on a subset of the large-scale dataset [LAION-5B](https://laion.ai/blog/laion-5b/), which contains adult, violent and sexual content. To partially mitigate this, we have filtered the dataset using LAION's NFSW detector (see Training section). ### Bias While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases. Stable Diffusion was primarily trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/), which consists of images that are limited to English descriptions. Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for. This affects the overall output of the model, as white and western cultures are often set as the default. Further, the ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts. Stable Diffusion v2 mirrors and exacerbates biases to such a degree that viewer discretion must be advised irrespective of the input or its intent. ## Training **Training Data** The model developers used the following dataset for training the model: - LAION-5B and subsets (details below). The training data is further filtered using LAION's NSFW detector, with a "p_unsafe" score of 0.1 (conservative). For more details, please refer to LAION-5B's [NeurIPS 2022](https://openreview.net/forum?id=M3Y74vmsMcY) paper and reviewer discussions on the topic. **Training Procedure** Stable Diffusion v2 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training, - Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4 - Text prompts are encoded through the OpenCLIP-ViT/H text-encoder. - The output of the text encoder is fed into the UNet backbone of the latent diffusion model via cross-attention. - The loss is a reconstruction objective between the noise that was added to the latent and the prediction made by the UNet. We also use the so-called _v-objective_, see https://arxiv.org/abs/2202.00512. We currently provide the following checkpoints: - `512-base-ema.ckpt`: 550k steps at resolution `256x256` on a subset of [LAION-5B](https://laion.ai/blog/laion-5b/) filtered for explicit pornographic material, using the [LAION-NSFW classifier](https://github.com/LAION-AI/CLIP-based-NSFW-Detector) with `punsafe=0.1` and an [aesthetic score](https://github.com/christophschuhmann/improved-aesthetic-predictor) >= `4.5`. 850k steps at resolution `512x512` on the same dataset with resolution `>= 512x512`. - `768-v-ema.ckpt`: Resumed from `512-base-ema.ckpt` and trained for 150k steps using a [v-objective](https://arxiv.org/abs/2202.00512) on the same dataset. Resumed for another 140k steps on a `768x768` subset of our dataset. - `512-depth-ema.ckpt`: Resumed from `512-base-ema.ckpt` and finetuned for 200k steps. Added an extra input channel to process the (relative) depth prediction produced by [MiDaS](https://github.com/isl-org/MiDaS) (`dpt_hybrid`) which is used as an additional conditioning. The additional input channels of the U-Net which process this extra information were zero-initialized. - `512-inpainting-ema.ckpt`: Resumed from `512-base-ema.ckpt` and trained for another 200k steps. Follows the mask-generation strategy presented in [LAMA](https://github.com/saic-mdal/lama) which, in combination with the latent VAE representations of the masked image, are used as an additional conditioning. The additional input channels of the U-Net which process this extra information were zero-initialized. The same strategy was used to train the [1.5-inpainting checkpoint](https://huggingface.co/runwayml/stable-diffusion-inpainting). - `x4-upscaling-ema.ckpt`: Trained for 1.25M steps on a 10M subset of LAION containing images `>2048x2048`. The model was trained on crops of size `512x512` and is a text-guided [latent upscaling diffusion model](https://arxiv.org/abs/2112.10752). In addition to the textual input, it receives a `noise_level` as an input parameter, which can be used to add noise to the low-resolution input according to a [predefined diffusion schedule](configs/stable-diffusion/x4-upscaling.yaml). - **Hardware:** 32 x 8 x A100 GPUs - **Optimizer:** AdamW - **Gradient Accumulations**: 1 - **Batch:** 32 x 8 x 2 x 4 = 2048 - **Learning rate:** warmup to 0.0001 for 10,000 steps and then kept constant ## Evaluation Results Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0) and 50 steps DDIM sampling steps show the relative improvements of the checkpoints:  Evaluated using 50 DDIM steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution. Not optimized for FID scores. ## Environmental Impact **Stable Diffusion v1** **Estimated Emissions** Based on that information, we estimate the following CO2 emissions using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact. - **Hardware Type:** A100 PCIe 40GB - **Hours used:** 200000 - **Cloud Provider:** AWS - **Compute Region:** US-east - **Carbon Emitted (Power consumption x Time x Carbon produced based on location of power grid):** 15000 kg CO2 eq. ## Citation @InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} } *This model card was written by: Robin Rombach, Patrick Esser and David Ha and is based on the [Stable Diffusion v1](https://github.com/CompVis/stable-diffusion/blob/main/Stable_Diffusion_v1_Model_Card.md) and [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).*

sshleifer/tiny-gpt2

sshleifer

transformers

text-generation

Entry not found

BAAI/bge-reranker-large

BAAI

transformers

feature-extraction

--- license: mit language: - en - zh tags: - mteb model-index: - name: bge-reranker-base results: - task: type: Reranking dataset: type: C-MTEB/CMedQAv1-reranking name: MTEB CMedQAv1 config: default split: test revision: None metrics: - type: map value: 81.27206722525007 - type: mrr value: 84.14238095238095 - task: type: Reranking dataset: type: C-MTEB/CMedQAv2-reranking name: MTEB CMedQAv2 config: default split: test revision: None metrics: - type: map value: 84.10369934291236 - type: mrr value: 86.79376984126984 - task: type: Reranking dataset: type: C-MTEB/Mmarco-reranking name: MTEB MMarcoReranking config: default split: dev revision: None metrics: - type: map value: 35.4600511272538 - type: mrr value: 34.60238095238095 - task: type: Reranking dataset: type: C-MTEB/T2Reranking name: MTEB T2Reranking config: default split: dev revision: None metrics: - type: map value: 67.27728847727172 - type: mrr value: 77.1315192743764 pipeline_tag: feature-extraction --- **We have updated the [new reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker), supporting larger lengths, more languages, and achieving better performance.** <h1 align="center">FlagEmbedding</h1> <h4 align="center"> <p> <a href=#model-list>Model List</a> | <a href=#frequently-asked-questions>FAQ</a> | <a href=#usage>Usage</a> | <a href="#evaluation">Evaluation</a> | <a href="#train">Train</a> | <a href="#citation">Citation</a> | <a href="#license">License</a> <p> </h4> **More details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).** [English](README.md) | [中文](https://github.com/FlagOpen/FlagEmbedding/blob/master/README_zh.md) FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - **Long-Context LLM**: [Activation Beacon](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/activation_beacon) - **Fine-tuning of LM** : [LM-Cocktail](https://github.com/FlagOpen/FlagEmbedding/tree/master/LM_Cocktail) - **Embedding Model**: [Visualized-BGE](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/visual), [BGE-M3](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3), [LLM Embedder](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder), [BGE Embedding](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/baai_general_embedding) - **Reranker Model**: [llm rerankers](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker), [BGE Reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker) - **Benchmark**: [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) ## News - 3/18/2024: Release new [rerankers](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker), built upon powerful M3 and LLM (GEMMA and MiniCPM, not so large actually) backbones, supporitng multi-lingual processing and larger inputs, massive improvements of ranking performances on BEIR, C-MTEB/Retrieval, MIRACL, LlamaIndex Evaluation. - 3/18/2024: Release [Visualized-BGE](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/visual), equipping BGE with visual capabilities. Visualized-BGE can be utilized to generate embeddings for hybrid image-text data. - 1/30/2024: Release **BGE-M3**, a new member to BGE model series! M3 stands for **M**ulti-linguality (100+ languages), **M**ulti-granularities (input length up to 8192), **M**ulti-Functionality (unification of dense, lexical, multi-vec/colbert retrieval). It is the first embedding model which supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks. [Technical Report](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/BGE_M3/BGE_M3.pdf) and [Code](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3). :fire: - 1/9/2024: Release [Activation-Beacon](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/activation_beacon), an effective, efficient, compatible, and low-cost (training) method to extend the context length of LLM. [Technical Report](https://arxiv.org/abs/2401.03462) :fire: - 12/24/2023: Release **LLaRA**, a LLaMA-7B based dense retriever, leading to state-of-the-art performances on MS MARCO and BEIR. Model and code will be open-sourced. Please stay tuned. [Technical Report](https://arxiv.org/abs/2312.15503) - 11/23/2023: Release [LM-Cocktail](https://github.com/FlagOpen/FlagEmbedding/tree/master/LM_Cocktail), a method to maintain general capabilities during fine-tuning by merging multiple language models. [Technical Report](https://arxiv.org/abs/2311.13534) :fire: - 10/12/2023: Release [LLM-Embedder](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder), a unified embedding model to support diverse retrieval augmentation needs for LLMs. [Technical Report](https://arxiv.org/pdf/2310.07554.pdf) - 09/15/2023: The [technical report](https://arxiv.org/pdf/2309.07597.pdf) of BGE has been released - 09/15/2023: The [massive training data](https://data.baai.ac.cn/details/BAAI-MTP) of BGE has been released - 09/12/2023: New models: - **New reranker model**: release cross-encoder models `BAAI/bge-reranker-base` and `BAAI/bge-reranker-large`, which are more powerful than embedding model. We recommend to use/fine-tune them to re-rank top-k documents returned by embedding models. - **update embedding model**: release `bge-*-v1.5` embedding model to alleviate the issue of the similarity distribution, and enhance its retrieval ability without instruction. <details> <summary>More</summary> <!-- ### More --> - 09/07/2023: Update [fine-tune code](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md): Add script to mine hard negatives and support adding instruction during fine-tuning. - 08/09/2023: BGE Models are integrated into **Langchain**, you can use it like [this](#using-langchain); C-MTEB **leaderboard** is [available](https://huggingface.co/spaces/mteb/leaderboard). - 08/05/2023: Release base-scale and small-scale models, **best performance among the models of the same size 🤗** - 08/02/2023: Release `bge-large-*`(short for BAAI General Embedding) Models, **rank 1st on MTEB and C-MTEB benchmark!** :tada: :tada: - 08/01/2023: We release the [Chinese Massive Text Embedding Benchmark](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB) (**C-MTEB**), consisting of 31 test dataset. </details> ## Model List `bge` is short for `BAAI general embedding`. | Model | Language | | Description | query instruction for retrieval [1] | |:-------------------------------|:--------:| :--------:| :--------:|:--------:| | [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | Multilingual | [Inference](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3#usage) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3) | Multi-Functionality(dense retrieval, sparse retrieval, multi-vector(colbert)), Multi-Linguality, and Multi-Granularity(8192 tokens) | | | [BAAI/llm-embedder](https://huggingface.co/BAAI/llm-embedder) | English | [Inference](./FlagEmbedding/llm_embedder/README.md) [Fine-tune](./FlagEmbedding/llm_embedder/README.md) | a unified embedding model to support diverse retrieval augmentation needs for LLMs | See [README](./FlagEmbedding/llm_embedder/README.md) | | [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | | | [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | | | [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` | | [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` | | [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` | | [BAAI/bge-large-zh-v1.5](https://huggingface.co/BAAI/bge-large-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` | | [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` | | [BAAI/bge-small-zh-v1.5](https://huggingface.co/BAAI/bge-small-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` | | [BAAI/bge-large-en](https://huggingface.co/BAAI/bge-large-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | :trophy: rank **1st** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: ` | | [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a base-scale model but with similar ability to `bge-large-en` | `Represent this sentence for searching relevant passages: ` | | [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) |a small-scale model but with competitive performance | `Represent this sentence for searching relevant passages: ` | | [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | :trophy: rank **1st** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark | `为这个句子生成表示以用于检索相关文章：` | | [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a base-scale model but with similar ability to `bge-large-zh` | `为这个句子生成表示以用于检索相关文章：` | | [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a small-scale model but with competitive performance | `为这个句子生成表示以用于检索相关文章：` | [1\]: If you need to search the relevant passages to a query, we suggest to add the instruction to the query; in other cases, no instruction is needed, just use the original query directly. In all cases, **no instruction** needs to be added to passages. [2\]: Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. To balance the accuracy and time cost, cross-encoder is widely used to re-rank top-k documents retrieved by other simple models. For examples, use bge embedding model to retrieve top 100 relevant documents, and then use bge reranker to re-rank the top 100 document to get the final top-3 results. All models have been uploaded to Huggingface Hub, and you can see them at https://huggingface.co/BAAI. If you cannot open the Huggingface Hub, you also can download the models at https://model.baai.ac.cn/models . ## Frequently asked questions <details> <summary>1. How to fine-tune bge embedding model?</summary> <!-- ### How to fine-tune bge embedding model? --> Following this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) to prepare data and fine-tune your model. Some suggestions: - Mine hard negatives following this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune#hard-negatives), which can improve the retrieval performance. - If you pre-train bge on your data, the pre-trained model cannot be directly used to calculate similarity, and it must be fine-tuned with contrastive learning before computing similarity. - If the accuracy of the fine-tuned model is still not high, it is recommended to use/fine-tune the cross-encoder model (bge-reranker) to re-rank top-k results. Hard negatives also are needed to fine-tune reranker. Refer to this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) for the fine-tuning for reranker </details> <details> <summary>2. The similarity score between two dissimilar sentences is higher than 0.5</summary> <!-- ### The similarity score between two dissimilar sentences is higher than 0.5 --> **Suggest to use bge v1.5, which alleviates the issue of the similarity distribution.** Since we finetune the models by contrastive learning with a temperature of 0.01, the similarity distribution of the current BGE model is about in the interval \[0.6, 1\]. So a similarity score greater than 0.5 does not indicate that the two sentences are similar. For downstream tasks, such as passage retrieval or semantic similarity, **what matters is the relative order of the scores, not the absolute value.** If you need to filter similar sentences based on a similarity threshold, please select an appropriate similarity threshold based on the similarity distribution on your data (such as 0.8, 0.85, or even 0.9). </details> <details> <summary>3. When does the query instruction need to be used</summary> <!-- ### When does the query instruction need to be used --> For the `bge-*-v1.5`, we improve its retrieval ability when not using instruction. No instruction only has a slight degradation in retrieval performance compared with using instruction. So you can generate embedding without instruction in all cases for convenience. For a retrieval task that uses short queries to find long related documents, it is recommended to add instructions for these short queries. **The best method to decide whether to add instructions for queries is choosing the setting that achieves better performance on your task.** In all cases, the documents/passages do not need to add the instruction. </details> ## Usage ### Usage for Embedding Model Here are some examples for using `bge` models with [FlagEmbedding](#using-flagembedding), [Sentence-Transformers](#using-sentence-transformers), [Langchain](#using-langchain), or [Huggingface Transformers](#using-huggingface-transformers). #### Using FlagEmbedding ``` pip install -U FlagEmbedding ``` If it doesn't work for you, you can see [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md) for more methods to install FlagEmbedding. ```python from FlagEmbedding import FlagModel sentences_1 = ["样例数据-1", "样例数据-2"] sentences_2 = ["样例数据-3", "样例数据-4"] model = FlagModel('BAAI/bge-large-zh-v1.5', query_instruction_for_retrieval="为这个句子生成表示以用于检索相关文章：", use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation embeddings_1 = model.encode(sentences_1) embeddings_2 = model.encode(sentences_2) similarity = embeddings_1 @ embeddings_2.T print(similarity) # for s2p(short query to long passage) retrieval task, suggest to use encode_queries() which will automatically add the instruction to each query # corpus in retrieval task can still use encode() or encode_corpus(), since they don't need instruction queries = ['query_1', 'query_2'] passages = ["样例文档-1", "样例文档-2"] q_embeddings = model.encode_queries(queries) p_embeddings = model.encode(passages) scores = q_embeddings @ p_embeddings.T ``` For the value of the argument `query_instruction_for_retrieval`, see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list). By default, FlagModel will use all available GPUs when encoding. Please set `os.environ["CUDA_VISIBLE_DEVICES"]` to select specific GPUs. You also can set `os.environ["CUDA_VISIBLE_DEVICES"]=""` to make all GPUs unavailable. #### Using Sentence-Transformers You can also use the `bge` models with [sentence-transformers](https://www.SBERT.net): ``` pip install -U sentence-transformers ``` ```python from sentence_transformers import SentenceTransformer sentences_1 = ["样例数据-1", "样例数据-2"] sentences_2 = ["样例数据-3", "样例数据-4"] model = SentenceTransformer('BAAI/bge-large-zh-v1.5') embeddings_1 = model.encode(sentences_1, normalize_embeddings=True) embeddings_2 = model.encode(sentences_2, normalize_embeddings=True) similarity = embeddings_1 @ embeddings_2.T print(similarity) ``` For s2p(short query to long passage) retrieval task, each short query should start with an instruction (instructions see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list)). But the instruction is not needed for passages. ```python from sentence_transformers import SentenceTransformer queries = ['query_1', 'query_2'] passages = ["样例文档-1", "样例文档-2"] instruction = "为这个句子生成表示以用于检索相关文章：" model = SentenceTransformer('BAAI/bge-large-zh-v1.5') q_embeddings = model.encode([instruction+q for q in queries], normalize_embeddings=True) p_embeddings = model.encode(passages, normalize_embeddings=True) scores = q_embeddings @ p_embeddings.T ``` #### Using Langchain You can use `bge` in langchain like this: ```python from langchain.embeddings import HuggingFaceBgeEmbeddings model_name = "BAAI/bge-large-en-v1.5" model_kwargs = {'device': 'cuda'} encode_kwargs = {'normalize_embeddings': True} # set True to compute cosine similarity model = HuggingFaceBgeEmbeddings( model_name=model_name, model_kwargs=model_kwargs, encode_kwargs=encode_kwargs, query_instruction="为这个句子生成表示以用于检索相关文章：" ) model.query_instruction = "为这个句子生成表示以用于检索相关文章：" ``` #### Using HuggingFace Transformers With the transformers package, you can use the model like this: First, you pass your input through the transformer model, then you select the last hidden state of the first token (i.e., [CLS]) as the sentence embedding. ```python from transformers import AutoTokenizer, AutoModel import torch # Sentences we want sentence embeddings for sentences = ["样例数据-1", "样例数据-2"] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-large-zh-v1.5') model = AutoModel.from_pretrained('BAAI/bge-large-zh-v1.5') model.eval() # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # for s2p(short query to long passage) retrieval task, add an instruction to query (not add instruction for passages) # encoded_input = tokenizer([instruction + q for q in queries], padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(**encoded_input) # Perform pooling. In this case, cls pooling. sentence_embeddings = model_output[0][:, 0] # normalize embeddings sentence_embeddings = torch.nn.functional.normalize(sentence_embeddings, p=2, dim=1) print("Sentence embeddings:", sentence_embeddings) ``` ### Usage for Reranker Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. The reranker is optimized based cross-entropy loss, so the relevance score is not bounded to a specific range. #### Using FlagEmbedding ``` pip install -U FlagEmbedding ``` Get relevance scores (higher scores indicate more relevance): ```python from FlagEmbedding import FlagReranker reranker = FlagReranker('BAAI/bge-reranker-large', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation score = reranker.compute_score(['query', 'passage']) print(score) scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']]) print(scores) ``` #### Using Huggingface transformers ```python import torch from transformers import AutoModelForSequenceClassification, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-large') model = AutoModelForSequenceClassification.from_pretrained('BAAI/bge-reranker-large') model.eval() pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']] with torch.no_grad(): inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512) scores = model(**inputs, return_dict=True).logits.view(-1, ).float() print(scores) ``` #### Usage reranker with the ONNX files ```python from optimum.onnxruntime import ORTModelForSequenceClassification # type: ignore import torch from transformers import AutoModelForSequenceClassification, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-large') model = AutoModelForSequenceClassification.from_pretrained('BAAI/bge-reranker-base') model_ort = ORTModelForSequenceClassification.from_pretrained('BAAI/bge-reranker-base', file_name="onnx/model.onnx") # Sentences we want sentence embeddings for pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']] # Tokenize sentences encoded_input = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt') scores_ort = model_ort(**encoded_input, return_dict=True).logits.view(-1, ).float() # Compute token embeddings with torch.inference_mode(): scores = model_ort(**encoded_input, return_dict=True).logits.view(-1, ).float() # scores and scores_ort are identical ``` #### Usage reranker with infinity Its also possible to deploy the onnx/torch files with the [infinity_emb](https://github.com/michaelfeil/infinity) pip package. ```python import asyncio from infinity_emb import AsyncEmbeddingEngine, EngineArgs query='what is a panda?' docs = ['The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear', "Paris is in France."] engine = AsyncEmbeddingEngine.from_args( EngineArgs(model_name_or_path = "BAAI/bge-reranker-base", device="cpu", engine="torch" # or engine="optimum" for onnx )) async def main(): async with engine: ranking, usage = await engine.rerank(query=query, docs=docs) print(list(zip(ranking, docs))) asyncio.run(main()) ``` ## Evaluation `baai-general-embedding` models achieve **state-of-the-art performance on both MTEB and C-MTEB leaderboard!** For more details and evaluation tools see our [scripts](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md). - **MTEB**: | Model Name | Dimension | Sequence Length | Average (56) | Retrieval (15) |Clustering (11) | Pair Classification (3) | Reranking (4) | STS (10) | Summarization (1) | Classification (12) | |:----:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:| | [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 | **64.23** | **54.29** | 46.08 | 87.12 | 60.03 | 83.11 | 31.61 | 75.97 | | [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | 768 | 512 | 63.55 | 53.25 | 45.77 | 86.55 | 58.86 | 82.4 | 31.07 | 75.53 | | [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | 384 | 512 | 62.17 |51.68 | 43.82 | 84.92 | 58.36 | 81.59 | 30.12 | 74.14 | | [bge-large-en](https://huggingface.co/BAAI/bge-large-en) | 1024 | 512 | 63.98 | 53.9 | 46.98 | 85.8 | 59.48 | 81.56 | 32.06 | 76.21 | | [bge-base-en](https://huggingface.co/BAAI/bge-base-en) | 768 | 512 | 63.36 | 53.0 | 46.32 | 85.86 | 58.7 | 81.84 | 29.27 | 75.27 | | [gte-large](https://huggingface.co/thenlper/gte-large) | 1024 | 512 | 63.13 | 52.22 | 46.84 | 85.00 | 59.13 | 83.35 | 31.66 | 73.33 | | [gte-base](https://huggingface.co/thenlper/gte-base) | 768 | 512 | 62.39 | 51.14 | 46.2 | 84.57 | 58.61 | 82.3 | 31.17 | 73.01 | | [e5-large-v2](https://huggingface.co/intfloat/e5-large-v2) | 1024| 512 | 62.25 | 50.56 | 44.49 | 86.03 | 56.61 | 82.05 | 30.19 | 75.24 | | [bge-small-en](https://huggingface.co/BAAI/bge-small-en) | 384 | 512 | 62.11 | 51.82 | 44.31 | 83.78 | 57.97 | 80.72 | 30.53 | 74.37 | | [instructor-xl](https://huggingface.co/hkunlp/instructor-xl) | 768 | 512 | 61.79 | 49.26 | 44.74 | 86.62 | 57.29 | 83.06 | 32.32 | 61.79 | | [e5-base-v2](https://huggingface.co/intfloat/e5-base-v2) | 768 | 512 | 61.5 | 50.29 | 43.80 | 85.73 | 55.91 | 81.05 | 30.28 | 73.84 | | [gte-small](https://huggingface.co/thenlper/gte-small) | 384 | 512 | 61.36 | 49.46 | 44.89 | 83.54 | 57.7 | 82.07 | 30.42 | 72.31 | | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) | 1536 | 8192 | 60.99 | 49.25 | 45.9 | 84.89 | 56.32 | 80.97 | 30.8 | 70.93 | | [e5-small-v2](https://huggingface.co/intfloat/e5-base-v2) | 384 | 512 | 59.93 | 49.04 | 39.92 | 84.67 | 54.32 | 80.39 | 31.16 | 72.94 | | [sentence-t5-xxl](https://huggingface.co/sentence-transformers/sentence-t5-xxl) | 768 | 512 | 59.51 | 42.24 | 43.72 | 85.06 | 56.42 | 82.63 | 30.08 | 73.42 | | [all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) | 768 | 514 | 57.78 | 43.81 | 43.69 | 83.04 | 59.36 | 80.28 | 27.49 | 65.07 | | [sgpt-bloom-7b1-msmarco](https://huggingface.co/bigscience/sgpt-bloom-7b1-msmarco) | 4096 | 2048 | 57.59 | 48.22 | 38.93 | 81.9 | 55.65 | 77.74 | 33.6 | 66.19 | - **C-MTEB**: We create the benchmark C-MTEB for Chinese text embedding which consists of 31 datasets from 6 tasks. Please refer to [C_MTEB](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md) for a detailed introduction. | Model | Embedding dimension | Avg | Retrieval | STS | PairClassification | Classification | Reranking | Clustering | |:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:| | [**BAAI/bge-large-zh-v1.5**](https://huggingface.co/BAAI/bge-large-zh-v1.5) | 1024 | **64.53** | 70.46 | 56.25 | 81.6 | 69.13 | 65.84 | 48.99 | | [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5) | 768 | 63.13 | 69.49 | 53.72 | 79.75 | 68.07 | 65.39 | 47.53 | | [BAAI/bge-small-zh-v1.5](https://huggingface.co/BAAI/bge-small-zh-v1.5) | 512 | 57.82 | 61.77 | 49.11 | 70.41 | 63.96 | 60.92 | 44.18 | | [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) | 1024 | 64.20 | 71.53 | 54.98 | 78.94 | 68.32 | 65.11 | 48.39 | | [bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct) | 1024 | 63.53 | 70.55 | 53 | 76.77 | 68.58 | 64.91 | 50.01 | | [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | 768 | 62.96 | 69.53 | 54.12 | 77.5 | 67.07 | 64.91 | 47.63 | | [multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) | 1024 | 58.79 | 63.66 | 48.44 | 69.89 | 67.34 | 56.00 | 48.23 | | [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | 512 | 58.27 | 63.07 | 49.45 | 70.35 | 63.64 | 61.48 | 45.09 | | [m3e-base](https://huggingface.co/moka-ai/m3e-base) | 768 | 57.10 | 56.91 | 50.47 | 63.99 | 67.52 | 59.34 | 47.68 | | [m3e-large](https://huggingface.co/moka-ai/m3e-large) | 1024 | 57.05 | 54.75 | 50.42 | 64.3 | 68.2 | 59.66 | 48.88 | | [multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) | 768 | 55.48 | 61.63 | 46.49 | 67.07 | 65.35 | 54.35 | 40.68 | | [multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) | 384 | 55.38 | 59.95 | 45.27 | 66.45 | 65.85 | 53.86 | 45.26 | | [text-embedding-ada-002(OpenAI)](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings) | 1536 | 53.02 | 52.0 | 43.35 | 69.56 | 64.31 | 54.28 | 45.68 | | [luotuo](https://huggingface.co/silk-road/luotuo-bert-medium) | 1024 | 49.37 | 44.4 | 42.78 | 66.62 | 61 | 49.25 | 44.39 | | [text2vec-base](https://huggingface.co/shibing624/text2vec-base-chinese) | 768 | 47.63 | 38.79 | 43.41 | 67.41 | 62.19 | 49.45 | 37.66 | | [text2vec-large](https://huggingface.co/GanymedeNil/text2vec-large-chinese) | 1024 | 47.36 | 41.94 | 44.97 | 70.86 | 60.66 | 49.16 | 30.02 | - **Reranking**: See [C_MTEB](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/) for evaluation script. | Model | T2Reranking | T2RerankingZh2En\* | T2RerankingEn2Zh\* | MMarcoReranking | CMedQAv1 | CMedQAv2 | Avg | |:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:| | text2vec-base-multilingual | 64.66 | 62.94 | 62.51 | 14.37 | 48.46 | 48.6 | 50.26 | | multilingual-e5-small | 65.62 | 60.94 | 56.41 | 29.91 | 67.26 | 66.54 | 57.78 | | multilingual-e5-large | 64.55 | 61.61 | 54.28 | 28.6 | 67.42 | 67.92 | 57.4 | | multilingual-e5-base | 64.21 | 62.13 | 54.68 | 29.5 | 66.23 | 66.98 | 57.29 | | m3e-base | 66.03 | 62.74 | 56.07 | 17.51 | 77.05 | 76.76 | 59.36 | | m3e-large | 66.13 | 62.72 | 56.1 | 16.46 | 77.76 | 78.27 | 59.57 | | bge-base-zh-v1.5 | 66.49 | 63.25 | 57.02 | 29.74 | 80.47 | 84.88 | 63.64 | | bge-large-zh-v1.5 | 65.74 | 63.39 | 57.03 | 28.74 | 83.45 | 85.44 | 63.97 | | [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | 67.28 | 63.95 | 60.45 | 35.46 | 81.26 | 84.1 | 65.42 | | [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | 67.6 | 64.03 | 61.44 | 37.16 | 82.15 | 84.18 | 66.09 | \* : T2RerankingZh2En and T2RerankingEn2Zh are cross-language retrieval tasks ## Train ### BAAI Embedding We pre-train the models using [retromae](https://github.com/staoxiao/RetroMAE) and train them on large-scale pairs data using contrastive learning. **You can fine-tune the embedding model on your data following our [examples](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune).** We also provide a [pre-train example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/pretrain). Note that the goal of pre-training is to reconstruct the text, and the pre-trained model cannot be used for similarity calculation directly, it needs to be fine-tuned. More training details for bge see [baai_general_embedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md). ### BGE Reranker Cross-encoder will perform full-attention over the input pair, which is more accurate than embedding model (i.e., bi-encoder) but more time-consuming than embedding model. Therefore, it can be used to re-rank the top-k documents returned by embedding model. We train the cross-encoder on a multilingual pair data, The data format is the same as embedding model, so you can fine-tune it easily following our [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker). More details please refer to [./FlagEmbedding/reranker/README.md](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker) ## Citation If you find this repository useful, please consider giving a star :star: and citation ``` @misc{bge_embedding, title={C-Pack: Packaged Resources To Advance General Chinese Embedding}, author={Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff}, year={2023}, eprint={2309.07597}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ## License FlagEmbedding is licensed under the [MIT License](https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE). The released models can be used for commercial purposes free of charge.

BAAI/bge-reranker-base

BAAI

sentence-transformers

text-classification

--- license: mit language: - en - zh tags: - mteb - text-embeddings-inference model-index: - name: bge-reranker-base results: - task: type: Reranking dataset: type: C-MTEB/CMedQAv1-reranking name: MTEB CMedQAv1 config: default split: test revision: None metrics: - type: map value: 81.27206722525007 - type: mrr value: 84.14238095238095 - task: type: Reranking dataset: type: C-MTEB/CMedQAv2-reranking name: MTEB CMedQAv2 config: default split: test revision: None metrics: - type: map value: 84.10369934291236 - type: mrr value: 86.79376984126984 - task: type: Reranking dataset: type: C-MTEB/Mmarco-reranking name: MTEB MMarcoReranking config: default split: dev revision: None metrics: - type: map value: 35.4600511272538 - type: mrr value: 34.60238095238095 - task: type: Reranking dataset: type: C-MTEB/T2Reranking name: MTEB T2Reranking config: default split: dev revision: None metrics: - type: map value: 67.27728847727172 - type: mrr value: 77.1315192743764 pipeline_tag: text-classification library_name: sentence-transformers --- **We have updated the [new reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker), supporting larger lengths, more languages, and achieving better performance.** <h1 align="center">FlagEmbedding</h1> <h4 align="center"> <p> <a href=#model-list>Model List</a> | <a href=#frequently-asked-questions>FAQ</a> | <a href=#usage>Usage</a> | <a href="#evaluation">Evaluation</a> | <a href="#train">Train</a> | <a href="#citation">Citation</a> | <a href="#license">License</a> <p> </h4> **More details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).** [English](README.md) | [中文](https://github.com/FlagOpen/FlagEmbedding/blob/master/README_zh.md) FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - **Long-Context LLM**: [Activation Beacon](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/activation_beacon) - **Fine-tuning of LM** : [LM-Cocktail](https://github.com/FlagOpen/FlagEmbedding/tree/master/LM_Cocktail) - **Embedding Model**: [Visualized-BGE](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/visual), [BGE-M3](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3), [LLM Embedder](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder), [BGE Embedding](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/baai_general_embedding) - **Reranker Model**: [llm rerankers](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker), [BGE Reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker) - **Benchmark**: [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) ## News - 3/18/2024: Release new [rerankers](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker), built upon powerful M3 and LLM (GEMMA and MiniCPM, not so large actually) backbones, supporitng multi-lingual processing and larger inputs, massive improvements of ranking performances on BEIR, C-MTEB/Retrieval, MIRACL, LlamaIndex Evaluation. - 3/18/2024: Release [Visualized-BGE](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/visual), equipping BGE with visual capabilities. Visualized-BGE can be utilized to generate embeddings for hybrid image-text data. - 1/30/2024: Release **BGE-M3**, a new member to BGE model series! M3 stands for **M**ulti-linguality (100+ languages), **M**ulti-granularities (input length up to 8192), **M**ulti-Functionality (unification of dense, lexical, multi-vec/colbert retrieval). It is the first embedding model which supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks. [Technical Report](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/BGE_M3/BGE_M3.pdf) and [Code](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3). :fire: - 1/9/2024: Release [Activation-Beacon](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/activation_beacon), an effective, efficient, compatible, and low-cost (training) method to extend the context length of LLM. [Technical Report](https://arxiv.org/abs/2401.03462) :fire: - 12/24/2023: Release **LLaRA**, a LLaMA-7B based dense retriever, leading to state-of-the-art performances on MS MARCO and BEIR. Model and code will be open-sourced. Please stay tuned. [Technical Report](https://arxiv.org/abs/2312.15503) - 11/23/2023: Release [LM-Cocktail](https://github.com/FlagOpen/FlagEmbedding/tree/master/LM_Cocktail), a method to maintain general capabilities during fine-tuning by merging multiple language models. [Technical Report](https://arxiv.org/abs/2311.13534) :fire: - 10/12/2023: Release [LLM-Embedder](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder), a unified embedding model to support diverse retrieval augmentation needs for LLMs. [Technical Report](https://arxiv.org/pdf/2310.07554.pdf) - 09/15/2023: The [technical report](https://arxiv.org/pdf/2309.07597.pdf) of BGE has been released - 09/15/2023: The [massive training data](https://data.baai.ac.cn/details/BAAI-MTP) of BGE has been released - 09/12/2023: New models: - **New reranker model**: release cross-encoder models `BAAI/bge-reranker-base` and `BAAI/bge-reranker-large`, which are more powerful than embedding model. We recommend to use/fine-tune them to re-rank top-k documents returned by embedding models. - **update embedding model**: release `bge-*-v1.5` embedding model to alleviate the issue of the similarity distribution, and enhance its retrieval ability without instruction. <details> <summary>More</summary> <!-- ### More --> - 09/07/2023: Update [fine-tune code](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md): Add script to mine hard negatives and support adding instruction during fine-tuning. - 08/09/2023: BGE Models are integrated into **Langchain**, you can use it like [this](#using-langchain); C-MTEB **leaderboard** is [available](https://huggingface.co/spaces/mteb/leaderboard). - 08/05/2023: Release base-scale and small-scale models, **best performance among the models of the same size 🤗** - 08/02/2023: Release `bge-large-*`(short for BAAI General Embedding) Models, **rank 1st on MTEB and C-MTEB benchmark!** :tada: :tada: - 08/01/2023: We release the [Chinese Massive Text Embedding Benchmark](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB) (**C-MTEB**), consisting of 31 test dataset. </details> ## Model List `bge` is short for `BAAI general embedding`. | Model | Language | | Description | query instruction for retrieval [1] | |:-------------------------------|:--------:| :--------:| :--------:|:--------:| | [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | Multilingual | [Inference](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3#usage) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3) | Multi-Functionality(dense retrieval, sparse retrieval, multi-vector(colbert)), Multi-Linguality, and Multi-Granularity(8192 tokens) | | | [BAAI/llm-embedder](https://huggingface.co/BAAI/llm-embedder) | English | [Inference](./FlagEmbedding/llm_embedder/README.md) [Fine-tune](./FlagEmbedding/llm_embedder/README.md) | a unified embedding model to support diverse retrieval augmentation needs for LLMs | See [README](./FlagEmbedding/llm_embedder/README.md) | | [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | | | [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | | | [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` | | [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` | | [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` | | [BAAI/bge-large-zh-v1.5](https://huggingface.co/BAAI/bge-large-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` | | [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` | | [BAAI/bge-small-zh-v1.5](https://huggingface.co/BAAI/bge-small-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` | | [BAAI/bge-large-en](https://huggingface.co/BAAI/bge-large-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | :trophy: rank **1st** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: ` | | [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a base-scale model but with similar ability to `bge-large-en` | `Represent this sentence for searching relevant passages: ` | | [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) |a small-scale model but with competitive performance | `Represent this sentence for searching relevant passages: ` | | [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | :trophy: rank **1st** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark | `为这个句子生成表示以用于检索相关文章：` | | [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a base-scale model but with similar ability to `bge-large-zh` | `为这个句子生成表示以用于检索相关文章：` | | [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a small-scale model but with competitive performance | `为这个句子生成表示以用于检索相关文章：` | [1\]: If you need to search the relevant passages to a query, we suggest to add the instruction to the query; in other cases, no instruction is needed, just use the original query directly. In all cases, **no instruction** needs to be added to passages. [2\]: Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. To balance the accuracy and time cost, cross-encoder is widely used to re-rank top-k documents retrieved by other simple models. For examples, use bge embedding model to retrieve top 100 relevant documents, and then use bge reranker to re-rank the top 100 document to get the final top-3 results. All models have been uploaded to Huggingface Hub, and you can see them at https://huggingface.co/BAAI. If you cannot open the Huggingface Hub, you also can download the models at https://model.baai.ac.cn/models . ## Frequently asked questions <details> <summary>1. How to fine-tune bge embedding model?</summary> <!-- ### How to fine-tune bge embedding model? --> Following this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) to prepare data and fine-tune your model. Some suggestions: - Mine hard negatives following this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune#hard-negatives), which can improve the retrieval performance. - If you pre-train bge on your data, the pre-trained model cannot be directly used to calculate similarity, and it must be fine-tuned with contrastive learning before computing similarity. - If the accuracy of the fine-tuned model is still not high, it is recommended to use/fine-tune the cross-encoder model (bge-reranker) to re-rank top-k results. Hard negatives also are needed to fine-tune reranker. Refer to this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) for the fine-tuning for reranker </details> <details> <summary>2. The similarity score between two dissimilar sentences is higher than 0.5</summary> <!-- ### The similarity score between two dissimilar sentences is higher than 0.5 --> **Suggest to use bge v1.5, which alleviates the issue of the similarity distribution.** Since we finetune the models by contrastive learning with a temperature of 0.01, the similarity distribution of the current BGE model is about in the interval \[0.6, 1\]. So a similarity score greater than 0.5 does not indicate that the two sentences are similar. For downstream tasks, such as passage retrieval or semantic similarity, **what matters is the relative order of the scores, not the absolute value.** If you need to filter similar sentences based on a similarity threshold, please select an appropriate similarity threshold based on the similarity distribution on your data (such as 0.8, 0.85, or even 0.9). </details> <details> <summary>3. When does the query instruction need to be used</summary> <!-- ### When does the query instruction need to be used --> For the `bge-*-v1.5`, we improve its retrieval ability when not using instruction. No instruction only has a slight degradation in retrieval performance compared with using instruction. So you can generate embedding without instruction in all cases for convenience. For a retrieval task that uses short queries to find long related documents, it is recommended to add instructions for these short queries. **The best method to decide whether to add instructions for queries is choosing the setting that achieves better performance on your task.** In all cases, the documents/passages do not need to add the instruction. </details> ## Usage ### Usage for Embedding Model Here are some examples for using `bge` models with [FlagEmbedding](#using-flagembedding), [Sentence-Transformers](#using-sentence-transformers), [Langchain](#using-langchain), or [Huggingface Transformers](#using-huggingface-transformers). #### Using FlagEmbedding ``` pip install -U FlagEmbedding ``` If it doesn't work for you, you can see [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md) for more methods to install FlagEmbedding. ```python from FlagEmbedding import FlagModel sentences_1 = ["样例数据-1", "样例数据-2"] sentences_2 = ["样例数据-3", "样例数据-4"] model = FlagModel('BAAI/bge-large-zh-v1.5', query_instruction_for_retrieval="为这个句子生成表示以用于检索相关文章：", use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation embeddings_1 = model.encode(sentences_1) embeddings_2 = model.encode(sentences_2) similarity = embeddings_1 @ embeddings_2.T print(similarity) # for s2p(short query to long passage) retrieval task, suggest to use encode_queries() which will automatically add the instruction to each query # corpus in retrieval task can still use encode() or encode_corpus(), since they don't need instruction queries = ['query_1', 'query_2'] passages = ["样例文档-1", "样例文档-2"] q_embeddings = model.encode_queries(queries) p_embeddings = model.encode(passages) scores = q_embeddings @ p_embeddings.T ``` For the value of the argument `query_instruction_for_retrieval`, see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list). By default, FlagModel will use all available GPUs when encoding. Please set `os.environ["CUDA_VISIBLE_DEVICES"]` to select specific GPUs. You also can set `os.environ["CUDA_VISIBLE_DEVICES"]=""` to make all GPUs unavailable. #### Using Sentence-Transformers You can also use the `bge` models with [sentence-transformers](https://www.SBERT.net): ``` pip install -U sentence-transformers ``` ```python from sentence_transformers import SentenceTransformer sentences_1 = ["样例数据-1", "样例数据-2"] sentences_2 = ["样例数据-3", "样例数据-4"] model = SentenceTransformer('BAAI/bge-large-zh-v1.5') embeddings_1 = model.encode(sentences_1, normalize_embeddings=True) embeddings_2 = model.encode(sentences_2, normalize_embeddings=True) similarity = embeddings_1 @ embeddings_2.T print(similarity) ``` For s2p(short query to long passage) retrieval task, each short query should start with an instruction (instructions see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list)). But the instruction is not needed for passages. ```python from sentence_transformers import SentenceTransformer queries = ['query_1', 'query_2'] passages = ["样例文档-1", "样例文档-2"] instruction = "为这个句子生成表示以用于检索相关文章：" model = SentenceTransformer('BAAI/bge-large-zh-v1.5') q_embeddings = model.encode([instruction+q for q in queries], normalize_embeddings=True) p_embeddings = model.encode(passages, normalize_embeddings=True) scores = q_embeddings @ p_embeddings.T ``` #### Using Langchain You can use `bge` in langchain like this: ```python from langchain.embeddings import HuggingFaceBgeEmbeddings model_name = "BAAI/bge-large-en-v1.5" model_kwargs = {'device': 'cuda'} encode_kwargs = {'normalize_embeddings': True} # set True to compute cosine similarity model = HuggingFaceBgeEmbeddings( model_name=model_name, model_kwargs=model_kwargs, encode_kwargs=encode_kwargs, query_instruction="为这个句子生成表示以用于检索相关文章：" ) model.query_instruction = "为这个句子生成表示以用于检索相关文章：" ``` #### Using HuggingFace Transformers With the transformers package, you can use the model like this: First, you pass your input through the transformer model, then you select the last hidden state of the first token (i.e., [CLS]) as the sentence embedding. ```python from transformers import AutoTokenizer, AutoModel import torch # Sentences we want sentence embeddings for sentences = ["样例数据-1", "样例数据-2"] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-large-zh-v1.5') model = AutoModel.from_pretrained('BAAI/bge-large-zh-v1.5') model.eval() # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # for s2p(short query to long passage) retrieval task, add an instruction to query (not add instruction for passages) # encoded_input = tokenizer([instruction + q for q in queries], padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(**encoded_input) # Perform pooling. In this case, cls pooling. sentence_embeddings = model_output[0][:, 0] # normalize embeddings sentence_embeddings = torch.nn.functional.normalize(sentence_embeddings, p=2, dim=1) print("Sentence embeddings:", sentence_embeddings) ``` ### Usage for Reranker Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. The reranker is optimized based cross-entropy loss, so the relevance score is not bounded to a specific range. #### Using FlagEmbedding ``` pip install -U FlagEmbedding ``` Get relevance scores (higher scores indicate more relevance): ```python from FlagEmbedding import FlagReranker reranker = FlagReranker('BAAI/bge-reranker-large', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation score = reranker.compute_score(['query', 'passage']) print(score) scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']]) print(scores) ``` #### Using Huggingface transformers ```python import torch from transformers import AutoModelForSequenceClassification, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-large') model = AutoModelForSequenceClassification.from_pretrained('BAAI/bge-reranker-large') model.eval() pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']] with torch.no_grad(): inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512) scores = model(**inputs, return_dict=True).logits.view(-1, ).float() print(scores) ``` #### Usage reranker with the ONNX files ```python from optimum.onnxruntime import ORTModelForSequenceClassification # type: ignore import torch from transformers import AutoModelForSequenceClassification, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-large') model = AutoModelForSequenceClassification.from_pretrained('BAAI/bge-reranker-base') model_ort = ORTModelForSequenceClassification.from_pretrained('BAAI/bge-reranker-base', file_name="onnx/model.onnx") # Sentences we want sentence embeddings for pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']] # Tokenize sentences encoded_input = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt') scores_ort = model_ort(**encoded_input, return_dict=True).logits.view(-1, ).float() # Compute token embeddings with torch.inference_mode(): scores = model_ort(**encoded_input, return_dict=True).logits.view(-1, ).float() # scores and scores_ort are identical ``` #### Usage reranker with infinity Its also possible to deploy the onnx/torch files with the [infinity_emb](https://github.com/michaelfeil/infinity) pip package. ```python import asyncio from infinity_emb import AsyncEmbeddingEngine, EngineArgs query='what is a panda?' docs = ['The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear', "Paris is in France."] engine = AsyncEmbeddingEngine.from_args( EngineArgs(model_name_or_path = "BAAI/bge-reranker-base", device="cpu", engine="torch" # or engine="optimum" for onnx )) async def main(): async with engine: ranking, usage = await engine.rerank(query=query, docs=docs) print(list(zip(ranking, docs))) asyncio.run(main()) ``` ## Evaluation `baai-general-embedding` models achieve **state-of-the-art performance on both MTEB and C-MTEB leaderboard!** For more details and evaluation tools see our [scripts](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md). - **MTEB**: | Model Name | Dimension | Sequence Length | Average (56) | Retrieval (15) |Clustering (11) | Pair Classification (3) | Reranking (4) | STS (10) | Summarization (1) | Classification (12) | |:----:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:| | [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 | **64.23** | **54.29** | 46.08 | 87.12 | 60.03 | 83.11 | 31.61 | 75.97 | | [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | 768 | 512 | 63.55 | 53.25 | 45.77 | 86.55 | 58.86 | 82.4 | 31.07 | 75.53 | | [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | 384 | 512 | 62.17 |51.68 | 43.82 | 84.92 | 58.36 | 81.59 | 30.12 | 74.14 | | [bge-large-en](https://huggingface.co/BAAI/bge-large-en) | 1024 | 512 | 63.98 | 53.9 | 46.98 | 85.8 | 59.48 | 81.56 | 32.06 | 76.21 | | [bge-base-en](https://huggingface.co/BAAI/bge-base-en) | 768 | 512 | 63.36 | 53.0 | 46.32 | 85.86 | 58.7 | 81.84 | 29.27 | 75.27 | | [gte-large](https://huggingface.co/thenlper/gte-large) | 1024 | 512 | 63.13 | 52.22 | 46.84 | 85.00 | 59.13 | 83.35 | 31.66 | 73.33 | | [gte-base](https://huggingface.co/thenlper/gte-base) | 768 | 512 | 62.39 | 51.14 | 46.2 | 84.57 | 58.61 | 82.3 | 31.17 | 73.01 | | [e5-large-v2](https://huggingface.co/intfloat/e5-large-v2) | 1024| 512 | 62.25 | 50.56 | 44.49 | 86.03 | 56.61 | 82.05 | 30.19 | 75.24 | | [bge-small-en](https://huggingface.co/BAAI/bge-small-en) | 384 | 512 | 62.11 | 51.82 | 44.31 | 83.78 | 57.97 | 80.72 | 30.53 | 74.37 | | [instructor-xl](https://huggingface.co/hkunlp/instructor-xl) | 768 | 512 | 61.79 | 49.26 | 44.74 | 86.62 | 57.29 | 83.06 | 32.32 | 61.79 | | [e5-base-v2](https://huggingface.co/intfloat/e5-base-v2) | 768 | 512 | 61.5 | 50.29 | 43.80 | 85.73 | 55.91 | 81.05 | 30.28 | 73.84 | | [gte-small](https://huggingface.co/thenlper/gte-small) | 384 | 512 | 61.36 | 49.46 | 44.89 | 83.54 | 57.7 | 82.07 | 30.42 | 72.31 | | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) | 1536 | 8192 | 60.99 | 49.25 | 45.9 | 84.89 | 56.32 | 80.97 | 30.8 | 70.93 | | [e5-small-v2](https://huggingface.co/intfloat/e5-base-v2) | 384 | 512 | 59.93 | 49.04 | 39.92 | 84.67 | 54.32 | 80.39 | 31.16 | 72.94 | | [sentence-t5-xxl](https://huggingface.co/sentence-transformers/sentence-t5-xxl) | 768 | 512 | 59.51 | 42.24 | 43.72 | 85.06 | 56.42 | 82.63 | 30.08 | 73.42 | | [all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) | 768 | 514 | 57.78 | 43.81 | 43.69 | 83.04 | 59.36 | 80.28 | 27.49 | 65.07 | | [sgpt-bloom-7b1-msmarco](https://huggingface.co/bigscience/sgpt-bloom-7b1-msmarco) | 4096 | 2048 | 57.59 | 48.22 | 38.93 | 81.9 | 55.65 | 77.74 | 33.6 | 66.19 | - **C-MTEB**: We create the benchmark C-MTEB for Chinese text embedding which consists of 31 datasets from 6 tasks. Please refer to [C_MTEB](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md) for a detailed introduction. | Model | Embedding dimension | Avg | Retrieval | STS | PairClassification | Classification | Reranking | Clustering | |:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:| | [**BAAI/bge-large-zh-v1.5**](https://huggingface.co/BAAI/bge-large-zh-v1.5) | 1024 | **64.53** | 70.46 | 56.25 | 81.6 | 69.13 | 65.84 | 48.99 | | [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5) | 768 | 63.13 | 69.49 | 53.72 | 79.75 | 68.07 | 65.39 | 47.53 | | [BAAI/bge-small-zh-v1.5](https://huggingface.co/BAAI/bge-small-zh-v1.5) | 512 | 57.82 | 61.77 | 49.11 | 70.41 | 63.96 | 60.92 | 44.18 | | [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) | 1024 | 64.20 | 71.53 | 54.98 | 78.94 | 68.32 | 65.11 | 48.39 | | [bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct) | 1024 | 63.53 | 70.55 | 53 | 76.77 | 68.58 | 64.91 | 50.01 | | [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | 768 | 62.96 | 69.53 | 54.12 | 77.5 | 67.07 | 64.91 | 47.63 | | [multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) | 1024 | 58.79 | 63.66 | 48.44 | 69.89 | 67.34 | 56.00 | 48.23 | | [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | 512 | 58.27 | 63.07 | 49.45 | 70.35 | 63.64 | 61.48 | 45.09 | | [m3e-base](https://huggingface.co/moka-ai/m3e-base) | 768 | 57.10 | 56.91 | 50.47 | 63.99 | 67.52 | 59.34 | 47.68 | | [m3e-large](https://huggingface.co/moka-ai/m3e-large) | 1024 | 57.05 | 54.75 | 50.42 | 64.3 | 68.2 | 59.66 | 48.88 | | [multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) | 768 | 55.48 | 61.63 | 46.49 | 67.07 | 65.35 | 54.35 | 40.68 | | [multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) | 384 | 55.38 | 59.95 | 45.27 | 66.45 | 65.85 | 53.86 | 45.26 | | [text-embedding-ada-002(OpenAI)](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings) | 1536 | 53.02 | 52.0 | 43.35 | 69.56 | 64.31 | 54.28 | 45.68 | | [luotuo](https://huggingface.co/silk-road/luotuo-bert-medium) | 1024 | 49.37 | 44.4 | 42.78 | 66.62 | 61 | 49.25 | 44.39 | | [text2vec-base](https://huggingface.co/shibing624/text2vec-base-chinese) | 768 | 47.63 | 38.79 | 43.41 | 67.41 | 62.19 | 49.45 | 37.66 | | [text2vec-large](https://huggingface.co/GanymedeNil/text2vec-large-chinese) | 1024 | 47.36 | 41.94 | 44.97 | 70.86 | 60.66 | 49.16 | 30.02 | - **Reranking**: See [C_MTEB](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/) for evaluation script. | Model | T2Reranking | T2RerankingZh2En\* | T2RerankingEn2Zh\* | MMarcoReranking | CMedQAv1 | CMedQAv2 | Avg | |:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:| | text2vec-base-multilingual | 64.66 | 62.94 | 62.51 | 14.37 | 48.46 | 48.6 | 50.26 | | multilingual-e5-small | 65.62 | 60.94 | 56.41 | 29.91 | 67.26 | 66.54 | 57.78 | | multilingual-e5-large | 64.55 | 61.61 | 54.28 | 28.6 | 67.42 | 67.92 | 57.4 | | multilingual-e5-base | 64.21 | 62.13 | 54.68 | 29.5 | 66.23 | 66.98 | 57.29 | | m3e-base | 66.03 | 62.74 | 56.07 | 17.51 | 77.05 | 76.76 | 59.36 | | m3e-large | 66.13 | 62.72 | 56.1 | 16.46 | 77.76 | 78.27 | 59.57 | | bge-base-zh-v1.5 | 66.49 | 63.25 | 57.02 | 29.74 | 80.47 | 84.88 | 63.64 | | bge-large-zh-v1.5 | 65.74 | 63.39 | 57.03 | 28.74 | 83.45 | 85.44 | 63.97 | | [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | 67.28 | 63.95 | 60.45 | 35.46 | 81.26 | 84.1 | 65.42 | | [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | 67.6 | 64.03 | 61.44 | 37.16 | 82.15 | 84.18 | 66.09 | \* : T2RerankingZh2En and T2RerankingEn2Zh are cross-language retrieval tasks ## Train ### BAAI Embedding We pre-train the models using [retromae](https://github.com/staoxiao/RetroMAE) and train them on large-scale pairs data using contrastive learning. **You can fine-tune the embedding model on your data following our [examples](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune).** We also provide a [pre-train example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/pretrain). Note that the goal of pre-training is to reconstruct the text, and the pre-trained model cannot be used for similarity calculation directly, it needs to be fine-tuned. More training details for bge see [baai_general_embedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md). ### BGE Reranker Cross-encoder will perform full-attention over the input pair, which is more accurate than embedding model (i.e., bi-encoder) but more time-consuming than embedding model. Therefore, it can be used to re-rank the top-k documents returned by embedding model. We train the cross-encoder on a multilingual pair data, The data format is the same as embedding model, so you can fine-tune it easily following our [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker). More details please refer to [./FlagEmbedding/reranker/README.md](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker) ## Citation If you find this repository useful, please consider giving a star :star: and citation ``` @misc{bge_embedding, title={C-Pack: Packaged Resources To Advance General Chinese Embedding}, author={Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff}, year={2023}, eprint={2309.07597}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ## License FlagEmbedding is licensed under the [MIT License](https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE). The released models can be used for commercial purposes free of charge.

BAAI/bge-m3

BAAI

sentence-transformers

sentence-similarity

--- pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity license: mit --- For more details please refer to our github repo: https://github.com/FlagOpen/FlagEmbedding # BGE-M3 ([paper](https://arxiv.org/pdf/2402.03216.pdf), [code](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3)) In this project, we introduce BGE-M3, which is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity. - Multi-Functionality: It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and sparse retrieval. - Multi-Linguality: It can support more than 100 working languages. - Multi-Granularity: It is able to process inputs of different granularities, spanning from short sentences to long documents of up to 8192 tokens. **Some suggestions for retrieval pipeline in RAG** We recommend to use the following pipeline: hybrid retrieval + re-ranking. - Hybrid retrieval leverages the strengths of various methods, offering higher accuracy and stronger generalization capabilities. A classic example: using both embedding retrieval and the BM25 algorithm. Now, you can try to use BGE-M3, which supports both embedding and sparse retrieval. This allows you to obtain token weights (similar to the BM25) without any additional cost when generate dense embeddings. To use hybrid retrieval, you can refer to [Vespa](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb ) and [Milvus](https://github.com/milvus-io/pymilvus/blob/master/examples/hello_hybrid_sparse_dense.py). - As cross-encoder models, re-ranker demonstrates higher accuracy than bi-encoder embedding model. Utilizing the re-ranking model (e.g., [bge-reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker), [bge-reranker-v2](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker)) after retrieval can further filter the selected text. ## News: - 2024/7/1: **We update the MIRACL evaluation results of BGE-M3**. To reproduce the new results, you can refer to: [bge-m3_miracl_2cr](https://huggingface.co/datasets/hanhainebula/bge-m3_miracl_2cr). We have also updated our [paper](https://arxiv.org/pdf/2402.03216) on arXiv. <details> <summary> Details </summary> The previous test results were lower because we mistakenly removed the passages that have the same id as the query from the search results. After correcting this mistake, the overall performance of BGE-M3 on MIRACL is higher than the previous results, but the experimental conclusion remains unchanged. The other results are not affected by this mistake. To reproduce the previous lower results, you need to add the `--remove-query` parameter when using `pyserini.search.faiss` or `pyserini.search.lucene` to search the passages. </details> - 2024/3/20: **Thanks Milvus team!** Now you can use hybrid retrieval of bge-m3 in Milvus: [pymilvus/examples /hello_hybrid_sparse_dense.py](https://github.com/milvus-io/pymilvus/blob/master/examples/hello_hybrid_sparse_dense.py). - 2024/3/8: **Thanks for the [experimental results](https://towardsdatascience.com/openai-vs-open-source-multilingual-embedding-models-e5ccb7c90f05) from @[Yannael](https://huggingface.co/Yannael). In this benchmark, BGE-M3 achieves top performance in both English and other languages, surpassing models such as OpenAI.** - 2024/3/2: Release unified fine-tuning [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/unified_finetune) and [data](https://huggingface.co/datasets/Shitao/bge-m3-data) - 2024/2/6: We release the [MLDR](https://huggingface.co/datasets/Shitao/MLDR) (a long document retrieval dataset covering 13 languages) and [evaluation pipeline](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR). - 2024/2/1: **Thanks for the excellent tool from Vespa.** You can easily use multiple modes of BGE-M3 following this [notebook](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb) ## Specs - Model | Model Name | Dimension | Sequence Length | Introduction | |:----:|:---:|:---:|:---:| | [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | 1024 | 8192 | multilingual; unified fine-tuning (dense, sparse, and colbert) from bge-m3-unsupervised| | [BAAI/bge-m3-unsupervised](https://huggingface.co/BAAI/bge-m3-unsupervised) | 1024 | 8192 | multilingual; contrastive learning from bge-m3-retromae | | [BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) | -- | 8192 | multilingual; extend the max_length of [xlm-roberta](https://huggingface.co/FacebookAI/xlm-roberta-large) to 8192 and further pretrained via [retromae](https://github.com/staoxiao/RetroMAE)| | [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 | English model | | [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | 768 | 512 | English model | | [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | 384 | 512 | English model | - Data | Dataset | Introduction | |:----------------------------------------------------------:|:-------------------------------------------------:| | [MLDR](https://huggingface.co/datasets/Shitao/MLDR) | Docuemtn Retrieval Dataset, covering 13 languages | | [bge-m3-data](https://huggingface.co/datasets/Shitao/bge-m3-data) | Fine-tuning data used by bge-m3 | ## FAQ **1. Introduction for different retrieval methods** - Dense retrieval: map the text into a single embedding, e.g., [DPR](https://arxiv.org/abs/2004.04906), [BGE-v1.5](https://github.com/FlagOpen/FlagEmbedding) - Sparse retrieval (lexical matching): a vector of size equal to the vocabulary, with the majority of positions set to zero, calculating a weight only for tokens present in the text. e.g., BM25, [unicoil](https://arxiv.org/pdf/2106.14807.pdf), and [splade](https://arxiv.org/abs/2107.05720) - Multi-vector retrieval: use multiple vectors to represent a text, e.g., [ColBERT](https://arxiv.org/abs/2004.12832). **2. How to use BGE-M3 in other projects?** For embedding retrieval, you can employ the BGE-M3 model using the same approach as BGE. The only difference is that the BGE-M3 model no longer requires adding instructions to the queries. For hybrid retrieval, you can use [Vespa](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb ) and [Milvus](https://github.com/milvus-io/pymilvus/blob/master/examples/hello_hybrid_sparse_dense.py). **3. How to fine-tune bge-M3 model?** You can follow the common in this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) to fine-tune the dense embedding. If you want to fine-tune all embedding function of m3 (dense, sparse and colbert), you can refer to the [unified_fine-tuning example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/unified_finetune) ## Usage Install: ``` git clone https://github.com/FlagOpen/FlagEmbedding.git cd FlagEmbedding pip install -e . ``` or: ``` pip install -U FlagEmbedding ``` ### Generate Embedding for text - Dense Embedding ```python from FlagEmbedding import BGEM3FlagModel model = BGEM3FlagModel('BAAI/bge-m3', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation sentences_1 = ["What is BGE M3?", "Defination of BM25"] sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"] embeddings_1 = model.encode(sentences_1, batch_size=12, max_length=8192, # If you don't need such a long length, you can set a smaller value to speed up the encoding process. )['dense_vecs'] embeddings_2 = model.encode(sentences_2)['dense_vecs'] similarity = embeddings_1 @ embeddings_2.T print(similarity) # [[0.6265, 0.3477], [0.3499, 0.678 ]] ``` You also can use sentence-transformers and huggingface transformers to generate dense embeddings. Refer to [baai_general_embedding](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/baai_general_embedding#usage) for details. - Sparse Embedding (Lexical Weight) ```python from FlagEmbedding import BGEM3FlagModel model = BGEM3FlagModel('BAAI/bge-m3', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation sentences_1 = ["What is BGE M3?", "Defination of BM25"] sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"] output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=False) output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=False) # you can see the weight for each token: print(model.convert_id_to_token(output_1['lexical_weights'])) # [{'What': 0.08356, 'is': 0.0814, 'B': 0.1296, 'GE': 0.252, 'M': 0.1702, '3': 0.2695, '?': 0.04092}, # {'De': 0.05005, 'fin': 0.1368, 'ation': 0.04498, 'of': 0.0633, 'BM': 0.2515, '25': 0.3335}] # compute the scores via lexical mathcing lexical_scores = model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_2['lexical_weights'][0]) print(lexical_scores) # 0.19554901123046875 print(model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_1['lexical_weights'][1])) # 0.0 ``` - Multi-Vector (ColBERT) ```python from FlagEmbedding import BGEM3FlagModel model = BGEM3FlagModel('BAAI/bge-m3', use_fp16=True) sentences_1 = ["What is BGE M3?", "Defination of BM25"] sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"] output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=True) output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=True) print(model.colbert_score(output_1['colbert_vecs'][0], output_2['colbert_vecs'][0])) print(model.colbert_score(output_1['colbert_vecs'][0], output_2['colbert_vecs'][1])) # 0.7797 # 0.4620 ``` ### Compute score for text pairs Input a list of text pairs, you can get the scores computed by different methods. ```python from FlagEmbedding import BGEM3FlagModel model = BGEM3FlagModel('BAAI/bge-m3', use_fp16=True) sentences_1 = ["What is BGE M3?", "Defination of BM25"] sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"] sentence_pairs = [[i,j] for i in sentences_1 for j in sentences_2] print(model.compute_score(sentence_pairs, max_passage_length=128, # a smaller max length leads to a lower latency weights_for_different_modes=[0.4, 0.2, 0.4])) # weights_for_different_modes(w) is used to do weighted sum: w[0]*dense_score + w[1]*sparse_score + w[2]*colbert_score # { # 'colbert': [0.7796499729156494, 0.4621465802192688, 0.4523794651031494, 0.7898575067520142], # 'sparse': [0.195556640625, 0.00879669189453125, 0.0, 0.1802978515625], # 'dense': [0.6259765625, 0.347412109375, 0.349853515625, 0.67822265625], # 'sparse+dense': [0.482503205537796, 0.23454029858112335, 0.2332356721162796, 0.5122477412223816], # 'colbert+sparse+dense': [0.6013619303703308, 0.3255828022956848, 0.32089319825172424, 0.6232916116714478] # } ``` ## Evaluation We provide the evaluation script for [MKQA](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MKQA) and [MLDR](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR) ### Benchmarks from the open-source community  The BGE-M3 model emerged as the top performer on this benchmark (OAI is short for OpenAI). For more details, please refer to the [article](https://towardsdatascience.com/openai-vs-open-source-multilingual-embedding-models-e5ccb7c90f05) and [Github Repo](https://github.com/Yannael/multilingual-embeddings) ### Our results - Multilingual (Miracl dataset)  - Cross-lingual (MKQA dataset)  - Long Document Retrieval - MLDR:  Please note that [MLDR](https://huggingface.co/datasets/Shitao/MLDR) is a document retrieval dataset we constructed via LLM, covering 13 languages, including test set, validation set, and training set. We utilized the training set from MLDR to enhance the model's long document retrieval capabilities. Therefore, comparing baselines with `Dense w.o.long`(fine-tuning without long document dataset) is more equitable. Additionally, this long document retrieval dataset will be open-sourced to address the current lack of open-source multilingual long text retrieval datasets. We believe that this data will be helpful for the open-source community in training document retrieval models. - NarritiveQA:  - Comparison with BM25 We utilized Pyserini to implement BM25, and the test results can be reproduced by this [script](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR#bm25-baseline). We tested BM25 using two different tokenizers: one using Lucene Analyzer and the other using the same tokenizer as M3 (i.e., the tokenizer of xlm-roberta). The results indicate that BM25 remains a competitive baseline, especially in long document retrieval.  ## Training - Self-knowledge Distillation: combining multiple outputs from different retrieval modes as reward signal to enhance the performance of single mode(especially for sparse retrieval and multi-vec(colbert) retrival) - Efficient Batching: Improve the efficiency when fine-tuning on long text. The small-batch strategy is simple but effective, which also can used to fine-tune large embedding model. - MCLS: A simple method to improve the performance on long text without fine-tuning. If you have no enough resource to fine-tuning model with long text, the method is useful. Refer to our [report](https://arxiv.org/pdf/2402.03216.pdf) for more details. ## Acknowledgement Thanks to the authors of open-sourced datasets, including Miracl, MKQA, NarritiveQA, etc. Thanks to the open-sourced libraries like [Tevatron](https://github.com/texttron/tevatron), [Pyserini](https://github.com/castorini/pyserini). ## Citation If you find this repository useful, please consider giving a star :star: and citation ``` @misc{bge-m3, title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation}, author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu}, year={2024}, eprint={2402.03216}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

laion/CLIP-ViT-bigG-14-laion2B-39B-b160k

laion

open_clip

zero-shot-image-classification

--- license: mit widget: - src: >- https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png candidate_labels: playing music, playing sports example_title: Cat & Dog library_name: open_clip pipeline_tag: zero-shot-image-classification --- # Model Card for CLIP ViT-bigG/14 - LAION-2B # Table of Contents 1. [Model Details](#model-details) 2. [Uses](#uses) 3. [Training Details](#training-details) 4. [Evaluation](#evaluation) 5. [Acknowledgements](#acknowledgements) 6. [Citation](#citation) 7. [How To Get Started With the Model](#how-to-get-started-with-the-model) # Model Details ## Model Description A CLIP ViT-bigG/14 model trained with the LAION-2B English subset of LAION-5B (https://laion.ai/blog/laion-5b/) using OpenCLIP (https://github.com/mlfoundations/open_clip). Model training done by Mitchell Wortsman on the [stability.ai](https://stability.ai/) cluster. The license for this model is MIT. # Uses As per the original [OpenAI CLIP model card](https://github.com/openai/CLIP/blob/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1/model-card.md), this model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. We also hope it can be used for interdisciplinary studies of the potential impact of such model. The OpenAI CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis. Additionally, the LAION-5B blog (https://laion.ai/blog/laion-5b/) and upcoming paper include additional discussion as it relates specifically to the training dataset. ## Direct Use Zero-shot image classification, image and text retrieval, among others. ## Downstream Use Image classification and other image task fine-tuning, linear probe image classification, image generation guiding and conditioning, among others. ## Out-of-Scope Use As per the OpenAI models, **Any** deployed use case of the model - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment, are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task specific testing especially given the variability of CLIP’s performance with different class taxonomies. This makes untested and unconstrained deployment of the model in any use case currently potentially harmful. Certain use cases which would fall under the domain of surveillance and facial recognition are always out-of-scope regardless of performance of the model. This is because the use of artificial intelligence for tasks such as these can be premature currently given the lack of testing norms and checks to ensure its fair use. Since the model has not been purposefully trained in or evaluated on any languages other than English, its use should be limited to English language use cases. Further the above notice, the LAION-5B dataset used in training of these models has additional considerations, see below. # Training Details ## Training Data This model was trained with the 2 Billion sample English subset of LAION-5B (https://laion.ai/blog/laion-5b/). Fine-tuning was also partially done on LAION-A, a 900M subset of LAION-2B filtered with aesthetic V2 4.5+ and phash deduplicated. **IMPORTANT NOTE:** The motivation behind dataset creation is to democratize research and experimentation around large-scale multi-modal model training and handling of uncurated, large-scale datasets crawled from publically available internet. Our recommendation is therefore to use the dataset for research purposes. Be aware that this large-scale dataset is uncurated. Keep in mind that the uncurated nature of the dataset means that collected links may lead to strongly discomforting and disturbing content for a human viewer. Therefore, please use the demo links with caution and at your own risk. It is possible to extract a “safe” subset by filtering out samples based on the safety tags (using a customized trained NSFW classifier that we built). While this strongly reduces the chance for encountering potentially harmful content when viewing, we cannot entirely exclude the possibility for harmful content being still present in safe mode, so that the warning holds also there. We think that providing the dataset openly to broad research and other interested communities will allow for transparent investigation of benefits that come along with training large-scale models as well as pitfalls and dangers that may stay unreported or unnoticed when working with closed large datasets that remain restricted to a small community. Providing our dataset openly, we however do not recommend using it for creating ready-to-go industrial products, as the basic research about general properties and safety of such large-scale models, which we would like to encourage with this release, is still in progress. ## Training Procedure The training procedure will soon be discussed by a blog post on laion.ai. # Evaluation Evaluation done with code in the [LAION CLIP Benchmark suite](https://github.com/LAION-AI/CLIP_benchmark). ## Testing Data, Factors & Metrics ### Testing Data The testing is performed with VTAB+ (A combination of VTAB (https://arxiv.org/abs/1910.04867) w/ additional robustness datasets) for classification and COCO and Flickr for retrieval. **TODO** - more detail ## Results The model achieves a 80.1 zero-shot top-1 accuracy on ImageNet-1k. An initial round of benchmarks have been performed on a wider range of datasets, and will soon be visible at https://github.com/LAION-AI/CLIP_benchmark/blob/main/benchmark/results.ipynb **TODO** - create table for just this model's metrics. # Acknowledgements Acknowledging [stability.ai](https://stability.ai/) for the compute used to train this model. # Citation **BibTeX:** LAION-5B ```bibtex @inproceedings{schuhmann2022laionb, title={{LAION}-5B: An open large-scale dataset for training next generation image-text models}, author={Christoph Schuhmann and Romain Beaumont and Richard Vencu and Cade W Gordon and Ross Wightman and Mehdi Cherti and Theo Coombes and Aarush Katta and Clayton Mullis and Mitchell Wortsman and Patrick Schramowski and Srivatsa R Kundurthy and Katherine Crowson and Ludwig Schmidt and Robert Kaczmarczyk and Jenia Jitsev}, booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track}, year={2022}, url={https://openreview.net/forum?id=M3Y74vmsMcY} } ``` OpenAI CLIP paper ``` @inproceedings{Radford2021LearningTV, title={Learning Transferable Visual Models From Natural Language Supervision}, author={Alec Radford and Jong Wook Kim and Chris Hallacy and A. Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever}, booktitle={ICML}, year={2021} } ``` OpenCLIP software ``` @software{ilharco_gabriel_2021_5143773, author = {Ilharco, Gabriel and Wortsman, Mitchell and Wightman, Ross and Gordon, Cade and Carlini, Nicholas and Taori, Rohan and Dave, Achal and Shankar, Vaishaal and Namkoong, Hongseok and Miller, John and Hajishirzi, Hannaneh and Farhadi, Ali and Schmidt, Ludwig}, title = {OpenCLIP}, month = jul, year = 2021, note = {If you use this software, please cite it as below.}, publisher = {Zenodo}, version = {0.1}, doi = {10.5281/zenodo.5143773}, url = {https://doi.org/10.5281/zenodo.5143773} } ``` Scaling OpenCLIP paper ``` @article{cherti2022reproducible, title={Reproducible scaling laws for contrastive language-image learning}, author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia}, journal={arXiv preprint arXiv:2212.07143}, year={2022} } ``` # How to Get Started with the Model Use the code below to get started with the model. ** TODO ** - Hugging Face transformers, OpenCLIP, and timm getting started snippets

Systran/faster-whisper-large-v3

Systran

ctranslate2

automatic-speech-recognition

--- language: - en - zh - de - es - ru - ko - fr - ja - pt - tr - pl - ca - nl - ar - sv - it - id - hi - fi - vi - he - uk - el - ms - cs - ro - da - hu - ta - 'no' - th - ur - hr - bg - lt - la - mi - ml - cy - sk - te - fa - lv - bn - sr - az - sl - kn - et - mk - br - eu - is - hy - ne - mn - bs - kk - sq - sw - gl - mr - pa - si - km - sn - yo - so - af - oc - ka - be - tg - sd - gu - am - yi - lo - uz - fo - ht - ps - tk - nn - mt - sa - lb - my - bo - tl - mg - as - tt - haw - ln - ha - ba - jw - su - yue tags: - audio - automatic-speech-recognition license: mit library_name: ctranslate2 --- # Whisper large-v3 model for CTranslate2 This repository contains the conversion of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) to the [CTranslate2](https://github.com/OpenNMT/CTranslate2) model format. This model can be used in CTranslate2 or projects based on CTranslate2 such as [faster-whisper](https://github.com/systran/faster-whisper). ## Example ```python from faster_whisper import WhisperModel model = WhisperModel("large-v3") segments, info = model.transcribe("audio.mp3") for segment in segments: print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text)) ``` ## Conversion details The original model was converted with the following command: ``` ct2-transformers-converter --model openai/whisper-large-v3 --output_dir faster-whisper-large-v3 \ --copy_files tokenizer.json preprocessor_config.json --quantization float16 ``` Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the [`compute_type` option in CTranslate2](https://opennmt.net/CTranslate2/quantization.html). ## More information **For more information about the original model, see its [model card](https://huggingface.co/openai/whisper-large-v3).**

ibm-granite/granite-timeseries-ttm-v1

ibm-granite

transformers

--- license: apache-2.0 --- # TinyTimeMixer (TTM) Model Card <p align="center" width="100%"> <img src="ttm_image.webp" width="600"> </p> TinyTimeMixers (TTMs) are compact pre-trained models for Multivariate Time-Series Forecasting, open-sourced by IBM Research. **With less than 1 Million parameters, TTM introduces the notion of the first-ever “tiny” pre-trained models for Time-Series Forecasting.** TTM outperforms several popular benchmarks demanding billions of parameters in zero-shot and few-shot forecasting. TTMs are lightweight forecasters, pre-trained on publicly available time series data with various augmentations. TTM provides state-of-the-art zero-shot forecasts and can easily be fine-tuned for multi-variate forecasts with just 5% of the training data to be competitive. Refer to our [paper](https://arxiv.org/pdf/2401.03955v5.pdf) for more details. **The current open-source version supports point forecasting use-cases specifically ranging from minutely to hourly resolutions (Ex. 10 min, 15 min, 1 hour.).** **Note that zeroshot, fine-tuning and inference tasks using TTM can easily be executed in 1 GPU machine or in laptops too!!** **Recent updates:** We have developed more sophisticated variants of TTMs (TTM-B, TTM-E and TTM-A), featuring extended benchmarks that compare them with some of the latest models such as TimesFM, Moirai, Chronos, Lag-llama, and Moment. For full details, please refer to the latest version of our [paper](https://arxiv.org/pdf/2401.03955.pdf). Stay tuned for the release of the model weights for these newer variants. ## How to Get Started with the Model - [colab](https://colab.research.google.com/github/IBM/tsfm/blob/tutorial/notebooks/tutorial/ttm_tutorial.ipynb) - [Getting Started Notebook](https://github.com/IBM/tsfm/blob/main/notebooks/hfdemo/ttm_getting_started.ipynb) - [512-96 Benchmarks](https://github.com/IBM/tsfm/blob/main/notebooks/hfdemo/tinytimemixer/ttm_benchmarking_512_96.ipynb) - [1024-96 Benchmarks](https://github.com/IBM/tsfm/blob/main/notebooks/hfdemo/tinytimemixer/ttm_benchmarking_1024_96.ipynb) - Script for Finetuning with cross-channel correlation support - to be added soon ## Recommended Use 1. Users have to externally standard scale their data independently for every channel before feeding it to the model (Refer to [TSP](https://github.com/IBM/tsfm/blob/main/tsfm_public/toolkit/time_series_preprocessor.py), our data processing utility for data scaling.) 2. The current open-source version supports only minutely and hourly resolutions(Ex. 10 min, 15 min, 1 hour.). Other lower resolutions (say weekly, or monthly) are currently not supported in this version, as the model needs a minimum context length of 512 or 1024. 3. Enabling any upsampling or prepending zeros to virtually increase the context length for shorter-length datasets is not recommended and will impact the model performance. ## Benchmark Highlights: - TTM (with less than 1 Million parameters) outperforms the following popular Pre-trained SOTAs demanding several hundred Million to Billions of parameters [paper](https://arxiv.org/pdf/2401.03955v5.pdf): - *GPT4TS (NeurIPS 23) by 7-12% in few-shot forecasting* - *LLMTime (NeurIPS 23) by 24% in zero-shot forecasting*. - *SimMTM (NeurIPS 23) by 17% in few-shot forecasting*. - *Time-LLM (ICLR 24) by 2-8% in few-shot forecasting* - *UniTime (WWW 24) by 27% in zero-shot forecasting.* - Zero-shot results of TTM surpass the *few-shot results of many popular SOTA approaches* including PatchTST (ICLR 23), PatchTSMixer (KDD 23), TimesNet (ICLR 23), DLinear (AAAI 23) and FEDFormer (ICML 22). - TTM (1024-96, released in this model card with 1M parameters) outperforms pre-trained MOIRAI-Small (14M parameters) by 10%, MOIRAI-Base (91M parameters) by 2% and MOIRAI-Large (311M parameters) by 3% on zero-shot forecasting (horizon = 96). [[notebook]](https://github.com/IBM/tsfm/blob/main/notebooks/hfdemo/tinytimemixer/ttm_benchmarking_1024_96.ipynb) - TTM quick fine-tuning also outperforms the competitive statistical baselines (Statistical ensemble and S-Naive) in M4-hourly dataset which existing pretrained TS models are finding difficult to outperform. [[notebook]](https://github.com/IBM/tsfm/blob/main/notebooks/hfdemo/tinytimemixer/ttm_m4_hourly.ipynb) - TTM takes only a *few seconds for zeroshot/inference* and a *few minutes for finetuning* in 1 GPU machine, as opposed to long timing-requirements and heavy computing infra needs of other existing pre-trained models. ## Model Description TTM falls under the category of “focused pre-trained models”, wherein each pre-trained TTM is tailored for a particular forecasting setting (governed by the context length and forecast length). Instead of building one massive model supporting all forecasting settings, we opt for the approach of constructing smaller pre-trained models, each focusing on a specific forecasting setting, thereby yielding more accurate results. Furthermore, this approach ensures that our models remain extremely small and exceptionally fast, facilitating easy deployment without demanding a ton of resources. Hence, in this model card, we plan to release several pre-trained TTMs that can cater to many common forecasting settings in practice. Additionally, we have released our source code along with our pretraining scripts that users can utilize to pretrain models on their own. Pretraining TTMs is very easy and fast, taking only 3-6 hours using 6 A100 GPUs, as opposed to several days or weeks in traditional approaches. Each pre-trained model will be released in a different branch name in this model card. Kindly access the required model using our getting started [notebook](https://github.com/IBM/tsfm/blob/main/notebooks/hfdemo/ttm_getting_started.ipynb) mentioning the branch name. ## Model Releases (along with the branch name where the models are stored): - **512-96:** Given the last 512 time-points (i.e. context length), this model can forecast up to next 96 time-points (i.e. forecast length) in future. This model is targeted towards a forecasting setting of context length 512 and forecast length 96 and recommended for hourly and minutely resolutions (Ex. 10 min, 15 min, 1 hour, etc). (branch name: main) - **1024-96:** Given the last 1024 time-points (i.e. context length), this model can forecast up to next 96 time-points (i.e. forecast length) in future. This model is targeted towards a long forecasting setting of context length 1024 and forecast length 96 and recommended for hourly and minutely resolutions (Ex. 10 min, 15 min, 1 hour, etc). (branch name: 1024-96-v1) - Stay tuned for more models ! ## Model Details For more details on TTM architecture and benchmarks, refer to our [paper](https://arxiv.org/pdf/2401.03955v5.pdf). TTM-1 currently supports 2 modes: - **Zeroshot forecasting**: Directly apply the pre-trained model on your target data to get an initial forecast (with no training). - **Finetuned forecasting**: Finetune the pre-trained model with a subset of your target data to further improve the forecast. **Since, TTM models are extremely small and fast, it is practically very easy to finetune the model with your available target data in few minutes to get more accurate forecasts.** The current release supports multivariate forecasting via both channel independence and channel-mixing approaches. Decoder Channel-Mixing can be enabled during fine-tuning for capturing strong channel-correlation patterns across time-series variates, a critical capability lacking in existing counterparts. In addition, TTM also supports exogenous infusion and categorical data which is not released as part of this version. Stay tuned for these extended features. ### Model Sources - **Repository:** https://github.com/IBM/tsfm/tree/main/tsfm_public/models/tinytimemixer - **Paper:** https://arxiv.org/pdf/2401.03955v5.pdf - **Paper (Newer variants, extended benchmarks):** https://arxiv.org/pdf/2401.03955.pdf ### External Blogs on TTM - https://aihorizonforecast.substack.com/p/tiny-time-mixersttms-powerful-zerofew - https://medium.com/@david.proietti_17/predicting-venetian-lagoon-tide-levels-with-multivariate-time-series-modeling-8bafdf229588 ## Uses ``` # Load Model from HF Model Hub mentioning the branch name in revision field model = TinyTimeMixerForPrediction.from_pretrained( "https://huggingface.co/ibm/TTM", revision="main" ) # Do zeroshot zeroshot_trainer = Trainer( model=model, args=zeroshot_forecast_args, ) ) zeroshot_output = zeroshot_trainer.evaluate(dset_test) # Freeze backbone and enable few-shot or finetuning: # freeze backbone for param in model.backbone.parameters(): param.requires_grad = False finetune_forecast_trainer = Trainer( model=model, args=finetune_forecast_args, train_dataset=dset_train, eval_dataset=dset_val, callbacks=[early_stopping_callback, tracking_callback], optimizers=(optimizer, scheduler), ) finetune_forecast_trainer.train() fewshot_output = finetune_forecast_trainer.evaluate(dset_test) ``` ## Training Data The TTM models were trained on a collection of datasets from the Monash Time Series Forecasting repository. The datasets used include: - Australian Electricity Demand: https://zenodo.org/records/4659727 - Australian Weather: https://zenodo.org/records/4654822 - Bitcoin dataset: https://zenodo.org/records/5122101 - KDD Cup 2018 dataset: https://zenodo.org/records/4656756 - London Smart Meters: https://zenodo.org/records/4656091 - Saugeen River Flow: https://zenodo.org/records/4656058 - Solar Power: https://zenodo.org/records/4656027 - Sunspots: https://zenodo.org/records/4654722 - Solar: https://zenodo.org/records/4656144 - US Births: https://zenodo.org/records/4656049 - Wind Farms Production data: https://zenodo.org/records/4654858 - Wind Power: https://zenodo.org/records/4656032 ## Citation [optional] Kindly cite the following paper, if you intend to use our model or its associated architectures/approaches in your work **BibTeX:** ``` @misc{ekambaram2024tiny, title={Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series}, author={Vijay Ekambaram and Arindam Jati and Pankaj Dayama and Sumanta Mukherjee and Nam H. Nguyen and Wesley M. Gifford and Chandra Reddy and Jayant Kalagnanam}, year={2024}, eprint={2401.03955}, archivePrefix={arXiv}, primaryClass={cs.LG} } ``` **APA:** Ekambaram, V., Jati, A., Dayama, P., Mukherjee, S., Nguyen, N. H., Gifford, W. M., … Kalagnanam, J. (2024). Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series. arXiv [Cs.LG]. Retrieved from http://arxiv.org/abs/2401.03955 ## Model Card Authors Vijay Ekambaram, Arindam Jati, Pankaj Dayama, Nam H. Nguyen, Wesley Gifford and Jayant Kalagnanam ## IBM Public Repository Disclosure: All content in this repository including code has been provided by IBM under the associated open source software license and IBM is under no obligation to provide enhancements, updates, or support. IBM developers produced this code as an open source project (not as an IBM product), and IBM makes no assertions as to the level of quality nor security, and will not be maintaining this code going forward.

xlnet/xlnet-large-cased

xlnet

transformers

text-generation

--- language: en license: mit datasets: - bookcorpus - wikipedia --- # XLNet (large-sized model) XLNet model pre-trained on English language. It was introduced in the paper [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://arxiv.org/abs/1906.08237) by Yang et al. and first released in [this repository](https://github.com/zihangdai/xlnet/). Disclaimer: The team releasing XLNet did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description XLNet is a new unsupervised language representation learning method based on a novel generalized permutation language modeling objective. Additionally, XLNet employs Transformer-XL as the backbone model, exhibiting excellent performance for language tasks involving long context. Overall, XLNet achieves state-of-the-art (SOTA) results on various downstream language tasks including question answering, natural language inference, sentiment analysis, and document ranking. ## Intended uses & limitations The model is mostly intended to be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?search=xlnet) to look for fine-tuned versions on a task that interests you. Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering. For tasks such as text generation, you should look at models like GPT2. ## Usage Here is how to use this model to get the features of a given text in PyTorch: ```python from transformers import XLNetTokenizer, XLNetModel tokenizer = XLNetTokenizer.from_pretrained('xlnet-large-cased') model = XLNetModel.from_pretrained('xlnet-large-cased') inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") outputs = model(**inputs) last_hidden_states = outputs.last_hidden_state ``` ### BibTeX entry and citation info ```bibtex @article{DBLP:journals/corr/abs-1906-08237, author = {Zhilin Yang and Zihang Dai and Yiming Yang and Jaime G. Carbonell and Ruslan Salakhutdinov and Quoc V. Le}, title = {XLNet: Generalized Autoregressive Pretraining for Language Understanding}, journal = {CoRR}, volume = {abs/1906.08237}, year = {2019}, url = {http://arxiv.org/abs/1906.08237}, eprinttype = {arXiv}, eprint = {1906.08237}, timestamp = {Mon, 24 Jun 2019 17:28:45 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1906-08237.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ```

rizvandwiki/gender-classification

rizvandwiki

transformers

image-classification

--- tags: - image-classification - pytorch - huggingpics metrics: - accuracy model-index: - name: gender-classification results: - task: name: Image Classification type: image-classification metrics: - name: Accuracy type: accuracy value: 0.9244444370269775 --- # gender-classification Autogenerated by HuggingPics🤗🖼️ Create your own image classifier for **anything** by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb). Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics). ## Example Images #### female  #### male 

marieke93/MiniLM-evidence-types

marieke93

transformers

text-classification

--- license: mit tags: - generated_from_trainer metrics: - accuracy model-index: - name: MiniLM-evidence-types results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # MiniLM-evidence-types This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the evidence types dataset. It achieved the following results on the evaluation set: - Loss: 1.8672 - Macro f1: 0.3726 - Weighted f1: 0.7030 - Accuracy: 0.7161 - Balanced accuracy: 0.3616 ## Training and evaluation data The data set, as well as the code that was used to fine tune this model can be found in the GitHub repository [BA-Thesis-Information-Science-Persuasion-Strategies](https://github.com/mariekevdh/BA-Thesis-Information-Science-Persuasion-Strategies) ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Macro f1 | Weighted f1 | Accuracy | Balanced accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:-----------------:| | 1.4106 | 1.0 | 250 | 1.2698 | 0.1966 | 0.6084 | 0.6735 | 0.2195 | | 1.1437 | 2.0 | 500 | 1.0985 | 0.3484 | 0.6914 | 0.7116 | 0.3536 | | 0.9714 | 3.0 | 750 | 1.0901 | 0.2606 | 0.6413 | 0.6446 | 0.2932 | | 0.8382 | 4.0 | 1000 | 1.0197 | 0.2764 | 0.7024 | 0.7237 | 0.2783 | | 0.7192 | 5.0 | 1250 | 1.0895 | 0.2847 | 0.6824 | 0.6963 | 0.2915 | | 0.6249 | 6.0 | 1500 | 1.1296 | 0.3487 | 0.6888 | 0.6948 | 0.3377 | | 0.5336 | 7.0 | 1750 | 1.1515 | 0.3591 | 0.6982 | 0.7024 | 0.3496 | | 0.4694 | 8.0 | 2000 | 1.1962 | 0.3626 | 0.7185 | 0.7314 | 0.3415 | | 0.4058 | 9.0 | 2250 | 1.3313 | 0.3121 | 0.6920 | 0.7085 | 0.3033 | | 0.3746 | 10.0 | 2500 | 1.3993 | 0.3628 | 0.6976 | 0.7047 | 0.3495 | | 0.3267 | 11.0 | 2750 | 1.5078 | 0.3560 | 0.6958 | 0.7055 | 0.3464 | | 0.2939 | 12.0 | 3000 | 1.5875 | 0.3685 | 0.6968 | 0.7062 | 0.3514 | | 0.2677 | 13.0 | 3250 | 1.6470 | 0.3606 | 0.6976 | 0.7070 | 0.3490 | | 0.2425 | 14.0 | 3500 | 1.7164 | 0.3714 | 0.7069 | 0.7207 | 0.3551 | | 0.2301 | 15.0 | 3750 | 1.8151 | 0.3597 | 0.6975 | 0.7123 | 0.3466 | | 0.2268 | 16.0 | 4000 | 1.7838 | 0.3940 | 0.7034 | 0.7123 | 0.3869 | | 0.201 | 17.0 | 4250 | 1.8328 | 0.3725 | 0.6964 | 0.7062 | 0.3704 | | 0.1923 | 18.0 | 4500 | 1.8788 | 0.3708 | 0.7019 | 0.7154 | 0.3591 | | 0.1795 | 19.0 | 4750 | 1.8574 | 0.3752 | 0.7031 | 0.7161 | 0.3619 | | 0.1713 | 20.0 | 5000 | 1.8672 | 0.3726 | 0.7030 | 0.7161 | 0.3616 | ### Framework versions - Transformers 4.19.2 - Pytorch 1.11.0+cu113 - Datasets 2.2.2 - Tokenizers 0.12.1

microsoft/table-transformer-structure-recognition

microsoft

transformers

object-detection

--- license: mit widget: - src: https://documentation.tricentis.com/tosca/1420/en/content/tbox/images/table.png example_title: Table --- # Table Transformer (fine-tuned for Table Structure Recognition) Table Transformer (DETR) model trained on PubTables1M. It was introduced in the paper [PubTables-1M: Towards Comprehensive Table Extraction From Unstructured Documents](https://arxiv.org/abs/2110.00061) by Smock et al. and first released in [this repository](https://github.com/microsoft/table-transformer). Disclaimer: The team releasing Table Transformer did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description The Table Transformer is equivalent to [DETR](https://huggingface.co/docs/transformers/model_doc/detr), a Transformer-based object detection model. Note that the authors decided to use the "normalize before" setting of DETR, which means that layernorm is applied before self- and cross-attention. ## Usage You can use the raw model for detecting the structure (like rows, columns) in tables. See the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/table-transformer) for more info.

google/flan-t5-xxl

google

transformers

text2text-generation

--- language: - en - fr - ro - de - multilingual widget: - text: "Translate to German: My name is Arthur" example_title: "Translation" - text: "Please answer to the following question. Who is going to be the next Ballon d'or?" example_title: "Question Answering" - text: "Q: Can Geoffrey Hinton have a conversation with George Washington? Give the rationale before answering." example_title: "Logical reasoning" - text: "Please answer the following question. What is the boiling point of Nitrogen?" example_title: "Scientific knowledge" - text: "Answer the following yes/no question. Can you write a whole Haiku in a single tweet?" example_title: "Yes/no question" - text: "Answer the following yes/no question by reasoning step-by-step. Can you write a whole Haiku in a single tweet?" example_title: "Reasoning task" - text: "Q: ( False or not False or False ) is? A: Let's think step by step" example_title: "Boolean Expressions" - text: "The square root of x is the cube root of y. What is y to the power of 2, if x = 4?" example_title: "Math reasoning" - text: "Premise: At my age you will probably have learnt one lesson. Hypothesis: It's not certain how many lessons you'll learn by your thirties. Does the premise entail the hypothesis?" example_title: "Premise and hypothesis" tags: - text2text-generation datasets: - svakulenk0/qrecc - taskmaster2 - djaym7/wiki_dialog - deepmind/code_contests - lambada - gsm8k - aqua_rat - esnli - quasc - qed license: apache-2.0 --- # Model Card for FLAN-T5 XXL <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/flan2_architecture.jpg" alt="drawing" width="600"/> # Table of Contents 0. [TL;DR](#TL;DR) 1. [Model Details](#model-details) 2. [Usage](#usage) 3. [Uses](#uses) 4. [Bias, Risks, and Limitations](#bias-risks-and-limitations) 5. [Training Details](#training-details) 6. [Evaluation](#evaluation) 7. [Environmental Impact](#environmental-impact) 8. [Citation](#citation) # TL;DR If you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1000 additional tasks covering also more languages. As mentioned in the first few lines of the abstract : > Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints,1 which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models. **Disclaimer**: Content from **this** model card has been written by the Hugging Face team, and parts of it were copy pasted from the [T5 model card](https://huggingface.co/t5-large). # Model Details ## Model Description - **Model type:** Language model - **Language(s) (NLP):** English, German, French - **License:** Apache 2.0 - **Related Models:** [All FLAN-T5 Checkpoints](https://huggingface.co/models?search=flan-t5) - **Original Checkpoints:** [All Original FLAN-T5 Checkpoints](https://github.com/google-research/t5x/blob/main/docs/models.md#flan-t5-checkpoints) - **Resources for more information:** - [Research paper](https://arxiv.org/pdf/2210.11416.pdf) - [GitHub Repo](https://github.com/google-research/t5x) - [Hugging Face FLAN-T5 Docs (Similar to T5) ](https://huggingface.co/docs/transformers/model_doc/t5) # Usage Find below some example scripts on how to use the model in `transformers`: ## Using the Pytorch model ### Running the model on a CPU <details> <summary> Click to expand </summary> ```python from transformers import T5Tokenizer, T5ForConditionalGeneration tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl") model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl") input_text = "translate English to German: How old are you?" input_ids = tokenizer(input_text, return_tensors="pt").input_ids outputs = model.generate(input_ids) print(tokenizer.decode(outputs[0])) ``` </details> ### Running the model on a GPU <details> <summary> Click to expand </summary> ```python # pip install accelerate from transformers import T5Tokenizer, T5ForConditionalGeneration tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl") model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto") input_text = "translate English to German: How old are you?" input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda") outputs = model.generate(input_ids) print(tokenizer.decode(outputs[0])) ``` </details> ### Running the model on a GPU using different precisions #### FP16 <details> <summary> Click to expand </summary> ```python # pip install accelerate import torch from transformers import T5Tokenizer, T5ForConditionalGeneration tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl") model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto", torch_dtype=torch.float16) input_text = "translate English to German: How old are you?" input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda") outputs = model.generate(input_ids) print(tokenizer.decode(outputs[0])) ``` </details> #### INT8 <details> <summary> Click to expand </summary> ```python # pip install bitsandbytes accelerate from transformers import T5Tokenizer, T5ForConditionalGeneration tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl") model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto", load_in_8bit=True) input_text = "translate English to German: How old are you?" input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda") outputs = model.generate(input_ids) print(tokenizer.decode(outputs[0])) ``` </details> # Uses ## Direct Use and Downstream Use The authors write in [the original paper's model card](https://arxiv.org/pdf/2210.11416.pdf) that: > The primary use is research on language models, including: research on zero-shot NLP tasks and in-context few-shot learning NLP tasks, such as reasoning, and question answering; advancing fairness and safety research, and understanding limitations of current large language models See the [research paper](https://arxiv.org/pdf/2210.11416.pdf) for further details. ## Out-of-Scope Use More information needed. # Bias, Risks, and Limitations The information below in this section are copied from the model's [official model card](https://arxiv.org/pdf/2210.11416.pdf): > Language models, including Flan-T5, can potentially be used for language generation in a harmful way, according to Rae et al. (2021). Flan-T5 should not be used directly in any application, without a prior assessment of safety and fairness concerns specific to the application. ## Ethical considerations and risks > Flan-T5 is fine-tuned on a large corpus of text data that was not filtered for explicit content or assessed for existing biases. As a result the model itself is potentially vulnerable to generating equivalently inappropriate content or replicating inherent biases in the underlying data. ## Known Limitations > Flan-T5 has not been tested in real world applications. ## Sensitive Use: > Flan-T5 should not be applied for any unacceptable use cases, e.g., generation of abusive speech. # Training Details ## Training Data The model was trained on a mixture of tasks, that includes the tasks described in the table below (from the original paper, figure 2):  ## Training Procedure According to the model card from the [original paper](https://arxiv.org/pdf/2210.11416.pdf): > These models are based on pretrained T5 (Raffel et al., 2020) and fine-tuned with instructions for better zero-shot and few-shot performance. There is one fine-tuned Flan model per T5 model size. The model has been trained on TPU v3 or TPU v4 pods, using [`t5x`](https://github.com/google-research/t5x) codebase together with [`jax`](https://github.com/google/jax). # Evaluation ## Testing Data, Factors & Metrics The authors evaluated the model on various tasks covering several languages (1836 in total). See the table below for some quantitative evaluation:  For full details, please check the [research paper](https://arxiv.org/pdf/2210.11416.pdf). ## Results For full results for FLAN-T5-XXL, see the [research paper](https://arxiv.org/pdf/2210.11416.pdf), Table 3. # Environmental Impact Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** Google Cloud TPU Pods - TPU v3 or TPU v4 | Number of chips ≥ 4. - **Hours used:** More information needed - **Cloud Provider:** GCP - **Compute Region:** More information needed - **Carbon Emitted:** More information needed # Citation **BibTeX:** ```bibtex @misc{https://doi.org/10.48550/arxiv.2210.11416, doi = {10.48550/ARXIV.2210.11416}, url = {https://arxiv.org/abs/2210.11416}, author = {Chung, Hyung Won and Hou, Le and Longpre, Shayne and Zoph, Barret and Tay, Yi and Fedus, William and Li, Eric and Wang, Xuezhi and Dehghani, Mostafa and Brahma, Siddhartha and Webson, Albert and Gu, Shixiang Shane and Dai, Zhuyun and Suzgun, Mirac and Chen, Xinyun and Chowdhery, Aakanksha and Narang, Sharan and Mishra, Gaurav and Yu, Adams and Zhao, Vincent and Huang, Yanping and Dai, Andrew and Yu, Hongkun and Petrov, Slav and Chi, Ed H. and Dean, Jeff and Devlin, Jacob and Roberts, Adam and Zhou, Denny and Le, Quoc V. and Wei, Jason}, keywords = {Machine Learning (cs.LG), Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Scaling Instruction-Finetuned Language Models}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```

unsloth/llama-3-8b-Instruct-bnb-4bit

unsloth

transformers

text-generation

--- language: - en license: apache-2.0 library_name: transformers tags: - unsloth - transformers - llama - llama-3 --- # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth! Directly quantized 4bit model with `bitsandbytes`. We have a Google Colab Tesla T4 notebook for Llama-3 8b here: https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk) [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy%20me%20a%20coffee%20button.png" width="200"/>](https://ko-fi.com/unsloth) [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) ## ✨ Finetune for Free All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face. | Unsloth supports | Free Notebooks | Performance | Memory use | |-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------| | **Llama-3 8b** | [▶️ Start on Colab](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing) | 2.4x faster | 58% less | | **Gemma 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing) | 2.4x faster | 58% less | | **Mistral 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less | | **Llama-2 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lBzz5KeZJKXjvivbYvmGarix9Ao6Wxe5?usp=sharing) | 2.2x faster | 43% less | | **TinyLlama** | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less | | **CodeLlama 34b** A100 | [▶️ Start on Colab](https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing) | 1.9x faster | 27% less | | **Mistral 7b** 1xT4 | [▶️ Start on Kaggle](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook) | 5x faster\* | 62% less | | **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less | - This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates. - This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr. - \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.

Babelscape/wikineural-multilingual-ner

Babelscape

transformers

token-classification

--- annotations_creators: - machine-generated language_creators: - machine-generated widget: - text: My name is Wolfgang and I live in Berlin. - text: George Washington went to Washington. - text: Mi nombre es Sarah y vivo en Londres. - text: Меня зовут Симона, и я живу в Риме. tags: - named-entity-recognition - sequence-tagger-model datasets: - Babelscape/wikineural language: - de - en - es - fr - it - nl - pl - pt - ru - multilingual license: - cc-by-nc-sa-4.0 pretty_name: wikineural-dataset source_datasets: - original task_categories: - structure-prediction task_ids: - named-entity-recognition --- # WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER This is the model card for the EMNLP 2021 paper [WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER](https://aclanthology.org/2021.findings-emnlp.215/). We fine-tuned a multilingual language model (mBERT) for 3 epochs on our [WikiNEuRal dataset](https://huggingface.co/datasets/Babelscape/wikineural) for Named Entity Recognition (NER). The resulting multilingual NER model supports the 9 languages covered by WikiNEuRal (de, en, es, fr, it, nl, pl, pt, ru), and it was trained on all 9 languages jointly. **If you use the model, please reference this work in your paper**: ```bibtex @inproceedings{tedeschi-etal-2021-wikineural-combined, title = "{W}iki{NE}u{R}al: {C}ombined Neural and Knowledge-based Silver Data Creation for Multilingual {NER}", author = "Tedeschi, Simone and Maiorca, Valentino and Campolungo, Niccol{\`o} and Cecconi, Francesco and Navigli, Roberto", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021", month = nov, year = "2021", address = "Punta Cana, Dominican Republic", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2021.findings-emnlp.215", pages = "2521--2533", abstract = "Multilingual Named Entity Recognition (NER) is a key intermediate task which is needed in many areas of NLP. In this paper, we address the well-known issue of data scarcity in NER, especially relevant when moving to a multilingual scenario, and go beyond current approaches to the creation of multilingual silver data for the task. We exploit the texts of Wikipedia and introduce a new methodology based on the effective combination of knowledge-based approaches and neural models, together with a novel domain adaptation technique, to produce high-quality training corpora for NER. We evaluate our datasets extensively on standard benchmarks for NER, yielding substantial improvements up to 6 span-based F1-score points over previous state-of-the-art systems for data creation.", } ``` The original repository for the paper can be found at [https://github.com/Babelscape/wikineural](https://github.com/Babelscape/wikineural). ## How to use You can use this model with Transformers *pipeline* for NER. ```python from transformers import AutoTokenizer, AutoModelForTokenClassification from transformers import pipeline tokenizer = AutoTokenizer.from_pretrained("Babelscape/wikineural-multilingual-ner") model = AutoModelForTokenClassification.from_pretrained("Babelscape/wikineural-multilingual-ner") nlp = pipeline("ner", model=model, tokenizer=tokenizer, grouped_entities=True) example = "My name is Wolfgang and I live in Berlin" ner_results = nlp(example) print(ner_results) ``` ## Limitations and bias This model is trained on WikiNEuRal, a state-of-the-art dataset for Multilingual NER automatically derived from Wikipedia. Therefore, it might not generalize well to all textual genres (e.g. news). On the other hand, models trained only on news articles (e.g. only on CoNLL03) have been proven to obtain much lower scores on encyclopedic articles. To obtain more robust systems, we encourage you to train a system on the combination of WikiNEuRal with other datasets (e.g. WikiNEuRal + CoNLL). ## Licensing Information Contents of this repository are restricted to only non-commercial research purposes under the [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/). Copyright of the dataset contents and models belongs to the original copyright holders.

intfloat/e5-base-v2

intfloat

sentence-transformers

sentence-similarity

--- tags: - mteb - Sentence Transformers - sentence-similarity - sentence-transformers model-index: - name: e5-base-v2 results: - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (en) config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 77.77611940298506 - type: ap value: 42.052710266606056 - type: f1 value: 72.12040628266567 - task: type: Classification dataset: type: mteb/amazon_polarity name: MTEB AmazonPolarityClassification config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 92.81012500000001 - type: ap value: 89.4213700757244 - type: f1 value: 92.8039091197065 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (en) config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 46.711999999999996 - type: f1 value: 46.11544975436018 - task: type: Retrieval dataset: type: arguana name: MTEB ArguAna config: default split: test revision: None metrics: - type: map_at_1 value: 23.186 - type: map_at_10 value: 36.632999999999996 - type: map_at_100 value: 37.842 - type: map_at_1000 value: 37.865 - type: map_at_3 value: 32.278 - type: map_at_5 value: 34.760999999999996 - type: mrr_at_1 value: 23.400000000000002 - type: mrr_at_10 value: 36.721 - type: mrr_at_100 value: 37.937 - type: mrr_at_1000 value: 37.96 - type: mrr_at_3 value: 32.302 - type: mrr_at_5 value: 34.894 - type: ndcg_at_1 value: 23.186 - type: ndcg_at_10 value: 44.49 - type: ndcg_at_100 value: 50.065000000000005 - type: ndcg_at_1000 value: 50.629999999999995 - type: ndcg_at_3 value: 35.461 - type: ndcg_at_5 value: 39.969 - type: precision_at_1 value: 23.186 - type: precision_at_10 value: 6.97 - type: precision_at_100 value: 0.951 - type: precision_at_1000 value: 0.099 - type: precision_at_3 value: 14.912 - type: precision_at_5 value: 11.152 - type: recall_at_1 value: 23.186 - type: recall_at_10 value: 69.70100000000001 - type: recall_at_100 value: 95.092 - type: recall_at_1000 value: 99.431 - type: recall_at_3 value: 44.737 - type: recall_at_5 value: 55.761 - task: type: Clustering dataset: type: mteb/arxiv-clustering-p2p name: MTEB ArxivClusteringP2P config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 46.10312401440185 - task: type: Clustering dataset: type: mteb/arxiv-clustering-s2s name: MTEB ArxivClusteringS2S config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 39.67275326095384 - task: type: Reranking dataset: type: mteb/askubuntudupquestions-reranking name: MTEB AskUbuntuDupQuestions config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 58.97793816337376 - type: mrr value: 72.76832431957087 - task: type: STS dataset: type: mteb/biosses-sts name: MTEB BIOSSES config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 83.11646947018187 - type: cos_sim_spearman value: 81.40064994975234 - type: euclidean_pearson value: 82.37355689019232 - type: euclidean_spearman value: 81.6777646977348 - type: manhattan_pearson value: 82.61101422716945 - type: manhattan_spearman value: 81.80427360442245 - task: type: Classification dataset: type: mteb/banking77 name: MTEB Banking77Classification config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 83.52922077922076 - type: f1 value: 83.45298679360866 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-p2p name: MTEB BiorxivClusteringP2P config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 37.495115019668496 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-s2s name: MTEB BiorxivClusteringS2S config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 32.724792944166765 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackAndroidRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 32.361000000000004 - type: map_at_10 value: 43.765 - type: map_at_100 value: 45.224 - type: map_at_1000 value: 45.35 - type: map_at_3 value: 40.353 - type: map_at_5 value: 42.195 - type: mrr_at_1 value: 40.629 - type: mrr_at_10 value: 50.458000000000006 - type: mrr_at_100 value: 51.06699999999999 - type: mrr_at_1000 value: 51.12 - type: mrr_at_3 value: 47.902 - type: mrr_at_5 value: 49.447 - type: ndcg_at_1 value: 40.629 - type: ndcg_at_10 value: 50.376 - type: ndcg_at_100 value: 55.065 - type: ndcg_at_1000 value: 57.196000000000005 - type: ndcg_at_3 value: 45.616 - type: ndcg_at_5 value: 47.646 - type: precision_at_1 value: 40.629 - type: precision_at_10 value: 9.785 - type: precision_at_100 value: 1.562 - type: precision_at_1000 value: 0.2 - type: precision_at_3 value: 22.031 - type: precision_at_5 value: 15.737000000000002 - type: recall_at_1 value: 32.361000000000004 - type: recall_at_10 value: 62.214000000000006 - type: recall_at_100 value: 81.464 - type: recall_at_1000 value: 95.905 - type: recall_at_3 value: 47.5 - type: recall_at_5 value: 53.69500000000001 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackEnglishRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 27.971 - type: map_at_10 value: 37.444 - type: map_at_100 value: 38.607 - type: map_at_1000 value: 38.737 - type: map_at_3 value: 34.504000000000005 - type: map_at_5 value: 36.234 - type: mrr_at_1 value: 35.35 - type: mrr_at_10 value: 43.441 - type: mrr_at_100 value: 44.147999999999996 - type: mrr_at_1000 value: 44.196000000000005 - type: mrr_at_3 value: 41.285 - type: mrr_at_5 value: 42.552 - type: ndcg_at_1 value: 35.35 - type: ndcg_at_10 value: 42.903999999999996 - type: ndcg_at_100 value: 47.406 - type: ndcg_at_1000 value: 49.588 - type: ndcg_at_3 value: 38.778 - type: ndcg_at_5 value: 40.788000000000004 - type: precision_at_1 value: 35.35 - type: precision_at_10 value: 8.083 - type: precision_at_100 value: 1.313 - type: precision_at_1000 value: 0.18 - type: precision_at_3 value: 18.769 - type: precision_at_5 value: 13.439 - type: recall_at_1 value: 27.971 - type: recall_at_10 value: 52.492000000000004 - type: recall_at_100 value: 71.642 - type: recall_at_1000 value: 85.488 - type: recall_at_3 value: 40.1 - type: recall_at_5 value: 45.800000000000004 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGamingRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 39.898 - type: map_at_10 value: 51.819 - type: map_at_100 value: 52.886 - type: map_at_1000 value: 52.941 - type: map_at_3 value: 48.619 - type: map_at_5 value: 50.493 - type: mrr_at_1 value: 45.391999999999996 - type: mrr_at_10 value: 55.230000000000004 - type: mrr_at_100 value: 55.887 - type: mrr_at_1000 value: 55.916 - type: mrr_at_3 value: 52.717000000000006 - type: mrr_at_5 value: 54.222 - type: ndcg_at_1 value: 45.391999999999996 - type: ndcg_at_10 value: 57.586999999999996 - type: ndcg_at_100 value: 61.745000000000005 - type: ndcg_at_1000 value: 62.83800000000001 - type: ndcg_at_3 value: 52.207 - type: ndcg_at_5 value: 54.925999999999995 - type: precision_at_1 value: 45.391999999999996 - type: precision_at_10 value: 9.21 - type: precision_at_100 value: 1.226 - type: precision_at_1000 value: 0.136 - type: precision_at_3 value: 23.177 - type: precision_at_5 value: 16.038 - type: recall_at_1 value: 39.898 - type: recall_at_10 value: 71.18900000000001 - type: recall_at_100 value: 89.082 - type: recall_at_1000 value: 96.865 - type: recall_at_3 value: 56.907 - type: recall_at_5 value: 63.397999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGisRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 22.706 - type: map_at_10 value: 30.818 - type: map_at_100 value: 32.038 - type: map_at_1000 value: 32.123000000000005 - type: map_at_3 value: 28.077 - type: map_at_5 value: 29.709999999999997 - type: mrr_at_1 value: 24.407 - type: mrr_at_10 value: 32.555 - type: mrr_at_100 value: 33.692 - type: mrr_at_1000 value: 33.751 - type: mrr_at_3 value: 29.848999999999997 - type: mrr_at_5 value: 31.509999999999998 - type: ndcg_at_1 value: 24.407 - type: ndcg_at_10 value: 35.624 - type: ndcg_at_100 value: 41.454 - type: ndcg_at_1000 value: 43.556 - type: ndcg_at_3 value: 30.217 - type: ndcg_at_5 value: 33.111000000000004 - type: precision_at_1 value: 24.407 - type: precision_at_10 value: 5.548 - type: precision_at_100 value: 0.8869999999999999 - type: precision_at_1000 value: 0.11100000000000002 - type: precision_at_3 value: 12.731 - type: precision_at_5 value: 9.22 - type: recall_at_1 value: 22.706 - type: recall_at_10 value: 48.772 - type: recall_at_100 value: 75.053 - type: recall_at_1000 value: 90.731 - type: recall_at_3 value: 34.421 - type: recall_at_5 value: 41.427 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackMathematicaRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 13.424 - type: map_at_10 value: 21.09 - type: map_at_100 value: 22.264999999999997 - type: map_at_1000 value: 22.402 - type: map_at_3 value: 18.312 - type: map_at_5 value: 19.874 - type: mrr_at_1 value: 16.915 - type: mrr_at_10 value: 25.258000000000003 - type: mrr_at_100 value: 26.228 - type: mrr_at_1000 value: 26.31 - type: mrr_at_3 value: 22.492 - type: mrr_at_5 value: 24.04 - type: ndcg_at_1 value: 16.915 - type: ndcg_at_10 value: 26.266000000000002 - type: ndcg_at_100 value: 32.08 - type: ndcg_at_1000 value: 35.086 - type: ndcg_at_3 value: 21.049 - type: ndcg_at_5 value: 23.508000000000003 - type: precision_at_1 value: 16.915 - type: precision_at_10 value: 5.1 - type: precision_at_100 value: 0.9329999999999999 - type: precision_at_1000 value: 0.131 - type: precision_at_3 value: 10.282 - type: precision_at_5 value: 7.836 - type: recall_at_1 value: 13.424 - type: recall_at_10 value: 38.179 - type: recall_at_100 value: 63.906 - type: recall_at_1000 value: 84.933 - type: recall_at_3 value: 23.878 - type: recall_at_5 value: 30.037999999999997 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackPhysicsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 26.154 - type: map_at_10 value: 35.912 - type: map_at_100 value: 37.211 - type: map_at_1000 value: 37.327 - type: map_at_3 value: 32.684999999999995 - type: map_at_5 value: 34.562 - type: mrr_at_1 value: 32.435 - type: mrr_at_10 value: 41.411 - type: mrr_at_100 value: 42.297000000000004 - type: mrr_at_1000 value: 42.345 - type: mrr_at_3 value: 38.771 - type: mrr_at_5 value: 40.33 - type: ndcg_at_1 value: 32.435 - type: ndcg_at_10 value: 41.785 - type: ndcg_at_100 value: 47.469 - type: ndcg_at_1000 value: 49.685 - type: ndcg_at_3 value: 36.618 - type: ndcg_at_5 value: 39.101 - type: precision_at_1 value: 32.435 - type: precision_at_10 value: 7.642 - type: precision_at_100 value: 1.244 - type: precision_at_1000 value: 0.163 - type: precision_at_3 value: 17.485 - type: precision_at_5 value: 12.57 - type: recall_at_1 value: 26.154 - type: recall_at_10 value: 54.111 - type: recall_at_100 value: 78.348 - type: recall_at_1000 value: 92.996 - type: recall_at_3 value: 39.189 - type: recall_at_5 value: 45.852 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackProgrammersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 26.308999999999997 - type: map_at_10 value: 35.524 - type: map_at_100 value: 36.774 - type: map_at_1000 value: 36.891 - type: map_at_3 value: 32.561 - type: map_at_5 value: 34.034 - type: mrr_at_1 value: 31.735000000000003 - type: mrr_at_10 value: 40.391 - type: mrr_at_100 value: 41.227000000000004 - type: mrr_at_1000 value: 41.288000000000004 - type: mrr_at_3 value: 37.938 - type: mrr_at_5 value: 39.193 - type: ndcg_at_1 value: 31.735000000000003 - type: ndcg_at_10 value: 41.166000000000004 - type: ndcg_at_100 value: 46.702 - type: ndcg_at_1000 value: 49.157000000000004 - type: ndcg_at_3 value: 36.274 - type: ndcg_at_5 value: 38.177 - type: precision_at_1 value: 31.735000000000003 - type: precision_at_10 value: 7.5569999999999995 - type: precision_at_100 value: 1.2109999999999999 - type: precision_at_1000 value: 0.16 - type: precision_at_3 value: 17.199 - type: precision_at_5 value: 12.123000000000001 - type: recall_at_1 value: 26.308999999999997 - type: recall_at_10 value: 53.083000000000006 - type: recall_at_100 value: 76.922 - type: recall_at_1000 value: 93.767 - type: recall_at_3 value: 39.262 - type: recall_at_5 value: 44.413000000000004 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.391250000000003 - type: map_at_10 value: 33.280166666666666 - type: map_at_100 value: 34.49566666666667 - type: map_at_1000 value: 34.61533333333333 - type: map_at_3 value: 30.52183333333333 - type: map_at_5 value: 32.06608333333333 - type: mrr_at_1 value: 29.105083333333337 - type: mrr_at_10 value: 37.44766666666666 - type: mrr_at_100 value: 38.32491666666667 - type: mrr_at_1000 value: 38.385666666666665 - type: mrr_at_3 value: 35.06883333333333 - type: mrr_at_5 value: 36.42066666666667 - type: ndcg_at_1 value: 29.105083333333337 - type: ndcg_at_10 value: 38.54358333333333 - type: ndcg_at_100 value: 43.833583333333344 - type: ndcg_at_1000 value: 46.215333333333334 - type: ndcg_at_3 value: 33.876 - type: ndcg_at_5 value: 36.05208333333333 - type: precision_at_1 value: 29.105083333333337 - type: precision_at_10 value: 6.823416666666665 - type: precision_at_100 value: 1.1270833333333334 - type: precision_at_1000 value: 0.15208333333333332 - type: precision_at_3 value: 15.696750000000002 - type: precision_at_5 value: 11.193499999999998 - type: recall_at_1 value: 24.391250000000003 - type: recall_at_10 value: 49.98808333333333 - type: recall_at_100 value: 73.31616666666666 - type: recall_at_1000 value: 89.96291666666667 - type: recall_at_3 value: 36.86666666666667 - type: recall_at_5 value: 42.54350000000001 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackStatsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 21.995 - type: map_at_10 value: 28.807 - type: map_at_100 value: 29.813000000000002 - type: map_at_1000 value: 29.903000000000002 - type: map_at_3 value: 26.636 - type: map_at_5 value: 27.912 - type: mrr_at_1 value: 24.847 - type: mrr_at_10 value: 31.494 - type: mrr_at_100 value: 32.381 - type: mrr_at_1000 value: 32.446999999999996 - type: mrr_at_3 value: 29.473 - type: mrr_at_5 value: 30.7 - type: ndcg_at_1 value: 24.847 - type: ndcg_at_10 value: 32.818999999999996 - type: ndcg_at_100 value: 37.835 - type: ndcg_at_1000 value: 40.226 - type: ndcg_at_3 value: 28.811999999999998 - type: ndcg_at_5 value: 30.875999999999998 - type: precision_at_1 value: 24.847 - type: precision_at_10 value: 5.244999999999999 - type: precision_at_100 value: 0.856 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_3 value: 12.577 - type: precision_at_5 value: 8.895999999999999 - type: recall_at_1 value: 21.995 - type: recall_at_10 value: 42.479 - type: recall_at_100 value: 65.337 - type: recall_at_1000 value: 83.23700000000001 - type: recall_at_3 value: 31.573 - type: recall_at_5 value: 36.684 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackTexRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 15.751000000000001 - type: map_at_10 value: 21.909 - type: map_at_100 value: 23.064 - type: map_at_1000 value: 23.205000000000002 - type: map_at_3 value: 20.138 - type: map_at_5 value: 20.973 - type: mrr_at_1 value: 19.305 - type: mrr_at_10 value: 25.647 - type: mrr_at_100 value: 26.659 - type: mrr_at_1000 value: 26.748 - type: mrr_at_3 value: 23.933 - type: mrr_at_5 value: 24.754 - type: ndcg_at_1 value: 19.305 - type: ndcg_at_10 value: 25.886 - type: ndcg_at_100 value: 31.56 - type: ndcg_at_1000 value: 34.799 - type: ndcg_at_3 value: 22.708000000000002 - type: ndcg_at_5 value: 23.838 - type: precision_at_1 value: 19.305 - type: precision_at_10 value: 4.677 - type: precision_at_100 value: 0.895 - type: precision_at_1000 value: 0.136 - type: precision_at_3 value: 10.771 - type: precision_at_5 value: 7.46 - type: recall_at_1 value: 15.751000000000001 - type: recall_at_10 value: 34.156 - type: recall_at_100 value: 59.899 - type: recall_at_1000 value: 83.08 - type: recall_at_3 value: 24.772 - type: recall_at_5 value: 28.009 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackUnixRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 23.34 - type: map_at_10 value: 32.383 - type: map_at_100 value: 33.629999999999995 - type: map_at_1000 value: 33.735 - type: map_at_3 value: 29.68 - type: map_at_5 value: 31.270999999999997 - type: mrr_at_1 value: 27.612 - type: mrr_at_10 value: 36.381 - type: mrr_at_100 value: 37.351 - type: mrr_at_1000 value: 37.411 - type: mrr_at_3 value: 33.893 - type: mrr_at_5 value: 35.353 - type: ndcg_at_1 value: 27.612 - type: ndcg_at_10 value: 37.714999999999996 - type: ndcg_at_100 value: 43.525000000000006 - type: ndcg_at_1000 value: 45.812999999999995 - type: ndcg_at_3 value: 32.796 - type: ndcg_at_5 value: 35.243 - type: precision_at_1 value: 27.612 - type: precision_at_10 value: 6.465 - type: precision_at_100 value: 1.0619999999999998 - type: precision_at_1000 value: 0.13699999999999998 - type: precision_at_3 value: 15.049999999999999 - type: precision_at_5 value: 10.764999999999999 - type: recall_at_1 value: 23.34 - type: recall_at_10 value: 49.856 - type: recall_at_100 value: 75.334 - type: recall_at_1000 value: 91.156 - type: recall_at_3 value: 36.497 - type: recall_at_5 value: 42.769 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWebmastersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.097 - type: map_at_10 value: 34.599999999999994 - type: map_at_100 value: 36.174 - type: map_at_1000 value: 36.398 - type: map_at_3 value: 31.781 - type: map_at_5 value: 33.22 - type: mrr_at_1 value: 31.225 - type: mrr_at_10 value: 39.873 - type: mrr_at_100 value: 40.853 - type: mrr_at_1000 value: 40.904 - type: mrr_at_3 value: 37.681 - type: mrr_at_5 value: 38.669 - type: ndcg_at_1 value: 31.225 - type: ndcg_at_10 value: 40.586 - type: ndcg_at_100 value: 46.226 - type: ndcg_at_1000 value: 48.788 - type: ndcg_at_3 value: 36.258 - type: ndcg_at_5 value: 37.848 - type: precision_at_1 value: 31.225 - type: precision_at_10 value: 7.707999999999999 - type: precision_at_100 value: 1.536 - type: precision_at_1000 value: 0.242 - type: precision_at_3 value: 17.26 - type: precision_at_5 value: 12.253 - type: recall_at_1 value: 25.097 - type: recall_at_10 value: 51.602000000000004 - type: recall_at_100 value: 76.854 - type: recall_at_1000 value: 93.303 - type: recall_at_3 value: 38.68 - type: recall_at_5 value: 43.258 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWordpressRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 17.689 - type: map_at_10 value: 25.291000000000004 - type: map_at_100 value: 26.262 - type: map_at_1000 value: 26.372 - type: map_at_3 value: 22.916 - type: map_at_5 value: 24.315 - type: mrr_at_1 value: 19.409000000000002 - type: mrr_at_10 value: 27.233 - type: mrr_at_100 value: 28.109 - type: mrr_at_1000 value: 28.192 - type: mrr_at_3 value: 24.892 - type: mrr_at_5 value: 26.278000000000002 - type: ndcg_at_1 value: 19.409000000000002 - type: ndcg_at_10 value: 29.809 - type: ndcg_at_100 value: 34.936 - type: ndcg_at_1000 value: 37.852000000000004 - type: ndcg_at_3 value: 25.179000000000002 - type: ndcg_at_5 value: 27.563 - type: precision_at_1 value: 19.409000000000002 - type: precision_at_10 value: 4.861 - type: precision_at_100 value: 0.8 - type: precision_at_1000 value: 0.116 - type: precision_at_3 value: 11.029 - type: precision_at_5 value: 7.985 - type: recall_at_1 value: 17.689 - type: recall_at_10 value: 41.724 - type: recall_at_100 value: 65.95299999999999 - type: recall_at_1000 value: 88.094 - type: recall_at_3 value: 29.621 - type: recall_at_5 value: 35.179 - task: type: Retrieval dataset: type: climate-fever name: MTEB ClimateFEVER config: default split: test revision: None metrics: - type: map_at_1 value: 10.581 - type: map_at_10 value: 18.944 - type: map_at_100 value: 20.812 - type: map_at_1000 value: 21.002000000000002 - type: map_at_3 value: 15.661 - type: map_at_5 value: 17.502000000000002 - type: mrr_at_1 value: 23.388 - type: mrr_at_10 value: 34.263 - type: mrr_at_100 value: 35.364000000000004 - type: mrr_at_1000 value: 35.409 - type: mrr_at_3 value: 30.586000000000002 - type: mrr_at_5 value: 32.928000000000004 - type: ndcg_at_1 value: 23.388 - type: ndcg_at_10 value: 26.56 - type: ndcg_at_100 value: 34.248 - type: ndcg_at_1000 value: 37.779 - type: ndcg_at_3 value: 21.179000000000002 - type: ndcg_at_5 value: 23.504 - type: precision_at_1 value: 23.388 - type: precision_at_10 value: 8.476 - type: precision_at_100 value: 1.672 - type: precision_at_1000 value: 0.233 - type: precision_at_3 value: 15.852 - type: precision_at_5 value: 12.73 - type: recall_at_1 value: 10.581 - type: recall_at_10 value: 32.512 - type: recall_at_100 value: 59.313 - type: recall_at_1000 value: 79.25 - type: recall_at_3 value: 19.912 - type: recall_at_5 value: 25.832 - task: type: Retrieval dataset: type: dbpedia-entity name: MTEB DBPedia config: default split: test revision: None metrics: - type: map_at_1 value: 9.35 - type: map_at_10 value: 20.134 - type: map_at_100 value: 28.975 - type: map_at_1000 value: 30.709999999999997 - type: map_at_3 value: 14.513000000000002 - type: map_at_5 value: 16.671 - type: mrr_at_1 value: 69.75 - type: mrr_at_10 value: 77.67699999999999 - type: mrr_at_100 value: 77.97500000000001 - type: mrr_at_1000 value: 77.985 - type: mrr_at_3 value: 76.292 - type: mrr_at_5 value: 77.179 - type: ndcg_at_1 value: 56.49999999999999 - type: ndcg_at_10 value: 42.226 - type: ndcg_at_100 value: 47.562 - type: ndcg_at_1000 value: 54.923 - type: ndcg_at_3 value: 46.564 - type: ndcg_at_5 value: 43.830000000000005 - type: precision_at_1 value: 69.75 - type: precision_at_10 value: 33.525 - type: precision_at_100 value: 11.035 - type: precision_at_1000 value: 2.206 - type: precision_at_3 value: 49.75 - type: precision_at_5 value: 42 - type: recall_at_1 value: 9.35 - type: recall_at_10 value: 25.793 - type: recall_at_100 value: 54.186 - type: recall_at_1000 value: 77.81 - type: recall_at_3 value: 15.770000000000001 - type: recall_at_5 value: 19.09 - task: type: Classification dataset: type: mteb/emotion name: MTEB EmotionClassification config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 46.945 - type: f1 value: 42.07407842992542 - task: type: Retrieval dataset: type: fever name: MTEB FEVER config: default split: test revision: None metrics: - type: map_at_1 value: 71.04599999999999 - type: map_at_10 value: 80.718 - type: map_at_100 value: 80.961 - type: map_at_1000 value: 80.974 - type: map_at_3 value: 79.49199999999999 - type: map_at_5 value: 80.32000000000001 - type: mrr_at_1 value: 76.388 - type: mrr_at_10 value: 85.214 - type: mrr_at_100 value: 85.302 - type: mrr_at_1000 value: 85.302 - type: mrr_at_3 value: 84.373 - type: mrr_at_5 value: 84.979 - type: ndcg_at_1 value: 76.388 - type: ndcg_at_10 value: 84.987 - type: ndcg_at_100 value: 85.835 - type: ndcg_at_1000 value: 86.04899999999999 - type: ndcg_at_3 value: 83.04 - type: ndcg_at_5 value: 84.22500000000001 - type: precision_at_1 value: 76.388 - type: precision_at_10 value: 10.35 - type: precision_at_100 value: 1.099 - type: precision_at_1000 value: 0.11399999999999999 - type: precision_at_3 value: 32.108 - type: precision_at_5 value: 20.033 - type: recall_at_1 value: 71.04599999999999 - type: recall_at_10 value: 93.547 - type: recall_at_100 value: 96.887 - type: recall_at_1000 value: 98.158 - type: recall_at_3 value: 88.346 - type: recall_at_5 value: 91.321 - task: type: Retrieval dataset: type: fiqa name: MTEB FiQA2018 config: default split: test revision: None metrics: - type: map_at_1 value: 19.8 - type: map_at_10 value: 31.979999999999997 - type: map_at_100 value: 33.876 - type: map_at_1000 value: 34.056999999999995 - type: map_at_3 value: 28.067999999999998 - type: map_at_5 value: 30.066 - type: mrr_at_1 value: 38.735 - type: mrr_at_10 value: 47.749 - type: mrr_at_100 value: 48.605 - type: mrr_at_1000 value: 48.644999999999996 - type: mrr_at_3 value: 45.165 - type: mrr_at_5 value: 46.646 - type: ndcg_at_1 value: 38.735 - type: ndcg_at_10 value: 39.883 - type: ndcg_at_100 value: 46.983000000000004 - type: ndcg_at_1000 value: 50.043000000000006 - type: ndcg_at_3 value: 35.943000000000005 - type: ndcg_at_5 value: 37.119 - type: precision_at_1 value: 38.735 - type: precision_at_10 value: 10.940999999999999 - type: precision_at_100 value: 1.836 - type: precision_at_1000 value: 0.23900000000000002 - type: precision_at_3 value: 23.817 - type: precision_at_5 value: 17.346 - type: recall_at_1 value: 19.8 - type: recall_at_10 value: 47.082 - type: recall_at_100 value: 73.247 - type: recall_at_1000 value: 91.633 - type: recall_at_3 value: 33.201 - type: recall_at_5 value: 38.81 - task: type: Retrieval dataset: type: hotpotqa name: MTEB HotpotQA config: default split: test revision: None metrics: - type: map_at_1 value: 38.102999999999994 - type: map_at_10 value: 60.547 - type: map_at_100 value: 61.466 - type: map_at_1000 value: 61.526 - type: map_at_3 value: 56.973 - type: map_at_5 value: 59.244 - type: mrr_at_1 value: 76.205 - type: mrr_at_10 value: 82.816 - type: mrr_at_100 value: 83.002 - type: mrr_at_1000 value: 83.009 - type: mrr_at_3 value: 81.747 - type: mrr_at_5 value: 82.467 - type: ndcg_at_1 value: 76.205 - type: ndcg_at_10 value: 69.15 - type: ndcg_at_100 value: 72.297 - type: ndcg_at_1000 value: 73.443 - type: ndcg_at_3 value: 64.07000000000001 - type: ndcg_at_5 value: 66.96600000000001 - type: precision_at_1 value: 76.205 - type: precision_at_10 value: 14.601 - type: precision_at_100 value: 1.7049999999999998 - type: precision_at_1000 value: 0.186 - type: precision_at_3 value: 41.202 - type: precision_at_5 value: 27.006000000000004 - type: recall_at_1 value: 38.102999999999994 - type: recall_at_10 value: 73.005 - type: recall_at_100 value: 85.253 - type: recall_at_1000 value: 92.795 - type: recall_at_3 value: 61.803 - type: recall_at_5 value: 67.515 - task: type: Classification dataset: type: mteb/imdb name: MTEB ImdbClassification config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 86.15 - type: ap value: 80.36282825265391 - type: f1 value: 86.07368510726472 - task: type: Retrieval dataset: type: msmarco name: MTEB MSMARCO config: default split: dev revision: None metrics: - type: map_at_1 value: 22.6 - type: map_at_10 value: 34.887 - type: map_at_100 value: 36.069 - type: map_at_1000 value: 36.115 - type: map_at_3 value: 31.067 - type: map_at_5 value: 33.300000000000004 - type: mrr_at_1 value: 23.238 - type: mrr_at_10 value: 35.47 - type: mrr_at_100 value: 36.599 - type: mrr_at_1000 value: 36.64 - type: mrr_at_3 value: 31.735999999999997 - type: mrr_at_5 value: 33.939 - type: ndcg_at_1 value: 23.252 - type: ndcg_at_10 value: 41.765 - type: ndcg_at_100 value: 47.402 - type: ndcg_at_1000 value: 48.562 - type: ndcg_at_3 value: 34.016999999999996 - type: ndcg_at_5 value: 38.016 - type: precision_at_1 value: 23.252 - type: precision_at_10 value: 6.569 - type: precision_at_100 value: 0.938 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 14.479000000000001 - type: precision_at_5 value: 10.722 - type: recall_at_1 value: 22.6 - type: recall_at_10 value: 62.919000000000004 - type: recall_at_100 value: 88.82 - type: recall_at_1000 value: 97.71600000000001 - type: recall_at_3 value: 41.896 - type: recall_at_5 value: 51.537 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (en) config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 93.69357045143639 - type: f1 value: 93.55489858177597 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (en) config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 75.31235750114 - type: f1 value: 57.891491963121155 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (en) config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 73.04303967720243 - type: f1 value: 70.51516022297616 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (en) config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 77.65299260255549 - type: f1 value: 77.49059766538576 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-p2p name: MTEB MedrxivClusteringP2P config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 31.458906115906597 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-s2s name: MTEB MedrxivClusteringS2S config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 28.9851513122443 - task: type: Reranking dataset: type: mteb/mind_small name: MTEB MindSmallReranking config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 31.2916268497217 - type: mrr value: 32.328276715593816 - task: type: Retrieval dataset: type: nfcorpus name: MTEB NFCorpus config: default split: test revision: None metrics: - type: map_at_1 value: 6.3740000000000006 - type: map_at_10 value: 13.089999999999998 - type: map_at_100 value: 16.512 - type: map_at_1000 value: 18.014 - type: map_at_3 value: 9.671000000000001 - type: map_at_5 value: 11.199 - type: mrr_at_1 value: 46.749 - type: mrr_at_10 value: 55.367 - type: mrr_at_100 value: 56.021 - type: mrr_at_1000 value: 56.058 - type: mrr_at_3 value: 53.30200000000001 - type: mrr_at_5 value: 54.773 - type: ndcg_at_1 value: 45.046 - type: ndcg_at_10 value: 35.388999999999996 - type: ndcg_at_100 value: 32.175 - type: ndcg_at_1000 value: 41.018 - type: ndcg_at_3 value: 40.244 - type: ndcg_at_5 value: 38.267 - type: precision_at_1 value: 46.749 - type: precision_at_10 value: 26.563 - type: precision_at_100 value: 8.074 - type: precision_at_1000 value: 2.099 - type: precision_at_3 value: 37.358000000000004 - type: precision_at_5 value: 33.003 - type: recall_at_1 value: 6.3740000000000006 - type: recall_at_10 value: 16.805999999999997 - type: recall_at_100 value: 31.871 - type: recall_at_1000 value: 64.098 - type: recall_at_3 value: 10.383000000000001 - type: recall_at_5 value: 13.166 - task: type: Retrieval dataset: type: nq name: MTEB NQ config: default split: test revision: None metrics: - type: map_at_1 value: 34.847 - type: map_at_10 value: 50.532 - type: map_at_100 value: 51.504000000000005 - type: map_at_1000 value: 51.528 - type: map_at_3 value: 46.219 - type: map_at_5 value: 48.868 - type: mrr_at_1 value: 39.137 - type: mrr_at_10 value: 53.157 - type: mrr_at_100 value: 53.839999999999996 - type: mrr_at_1000 value: 53.857 - type: mrr_at_3 value: 49.667 - type: mrr_at_5 value: 51.847 - type: ndcg_at_1 value: 39.108 - type: ndcg_at_10 value: 58.221000000000004 - type: ndcg_at_100 value: 62.021 - type: ndcg_at_1000 value: 62.57 - type: ndcg_at_3 value: 50.27199999999999 - type: ndcg_at_5 value: 54.623999999999995 - type: precision_at_1 value: 39.108 - type: precision_at_10 value: 9.397 - type: precision_at_100 value: 1.1520000000000001 - type: precision_at_1000 value: 0.12 - type: precision_at_3 value: 22.644000000000002 - type: precision_at_5 value: 16.141 - type: recall_at_1 value: 34.847 - type: recall_at_10 value: 78.945 - type: recall_at_100 value: 94.793 - type: recall_at_1000 value: 98.904 - type: recall_at_3 value: 58.56 - type: recall_at_5 value: 68.535 - task: type: Retrieval dataset: type: quora name: MTEB QuoraRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 68.728 - type: map_at_10 value: 82.537 - type: map_at_100 value: 83.218 - type: map_at_1000 value: 83.238 - type: map_at_3 value: 79.586 - type: map_at_5 value: 81.416 - type: mrr_at_1 value: 79.17999999999999 - type: mrr_at_10 value: 85.79299999999999 - type: mrr_at_100 value: 85.937 - type: mrr_at_1000 value: 85.938 - type: mrr_at_3 value: 84.748 - type: mrr_at_5 value: 85.431 - type: ndcg_at_1 value: 79.17 - type: ndcg_at_10 value: 86.555 - type: ndcg_at_100 value: 88.005 - type: ndcg_at_1000 value: 88.146 - type: ndcg_at_3 value: 83.557 - type: ndcg_at_5 value: 85.152 - type: precision_at_1 value: 79.17 - type: precision_at_10 value: 13.163 - type: precision_at_100 value: 1.52 - type: precision_at_1000 value: 0.156 - type: precision_at_3 value: 36.53 - type: precision_at_5 value: 24.046 - type: recall_at_1 value: 68.728 - type: recall_at_10 value: 94.217 - type: recall_at_100 value: 99.295 - type: recall_at_1000 value: 99.964 - type: recall_at_3 value: 85.646 - type: recall_at_5 value: 90.113 - task: type: Clustering dataset: type: mteb/reddit-clustering name: MTEB RedditClustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 56.15680266226348 - task: type: Clustering dataset: type: mteb/reddit-clustering-p2p name: MTEB RedditClusteringP2P config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 63.4318549229047 - task: type: Retrieval dataset: type: scidocs name: MTEB SCIDOCS config: default split: test revision: None metrics: - type: map_at_1 value: 4.353 - type: map_at_10 value: 10.956000000000001 - type: map_at_100 value: 12.873999999999999 - type: map_at_1000 value: 13.177 - type: map_at_3 value: 7.854 - type: map_at_5 value: 9.327 - type: mrr_at_1 value: 21.4 - type: mrr_at_10 value: 31.948999999999998 - type: mrr_at_100 value: 33.039 - type: mrr_at_1000 value: 33.106 - type: mrr_at_3 value: 28.449999999999996 - type: mrr_at_5 value: 30.535 - type: ndcg_at_1 value: 21.4 - type: ndcg_at_10 value: 18.694 - type: ndcg_at_100 value: 26.275 - type: ndcg_at_1000 value: 31.836 - type: ndcg_at_3 value: 17.559 - type: ndcg_at_5 value: 15.372 - type: precision_at_1 value: 21.4 - type: precision_at_10 value: 9.790000000000001 - type: precision_at_100 value: 2.0709999999999997 - type: precision_at_1000 value: 0.34099999999999997 - type: precision_at_3 value: 16.467000000000002 - type: precision_at_5 value: 13.54 - type: recall_at_1 value: 4.353 - type: recall_at_10 value: 19.892000000000003 - type: recall_at_100 value: 42.067 - type: recall_at_1000 value: 69.268 - type: recall_at_3 value: 10.042 - type: recall_at_5 value: 13.741999999999999 - task: type: STS dataset: type: mteb/sickr-sts name: MTEB SICK-R config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 83.75433886279843 - type: cos_sim_spearman value: 78.29727771767095 - type: euclidean_pearson value: 80.83057828506621 - type: euclidean_spearman value: 78.35203149750356 - type: manhattan_pearson value: 80.7403553891142 - type: manhattan_spearman value: 78.33670488531051 - task: type: STS dataset: type: mteb/sts12-sts name: MTEB STS12 config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 84.59999465280839 - type: cos_sim_spearman value: 75.79279003980383 - type: euclidean_pearson value: 82.29895375956758 - type: euclidean_spearman value: 77.33856514102094 - type: manhattan_pearson value: 82.22694214534756 - type: manhattan_spearman value: 77.3028993008695 - task: type: STS dataset: type: mteb/sts13-sts name: MTEB STS13 config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 83.09296929691297 - type: cos_sim_spearman value: 83.58056936846941 - type: euclidean_pearson value: 83.84067483060005 - type: euclidean_spearman value: 84.45155680480985 - type: manhattan_pearson value: 83.82353052971942 - type: manhattan_spearman value: 84.43030567861112 - task: type: STS dataset: type: mteb/sts14-sts name: MTEB STS14 config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 82.74616852320915 - type: cos_sim_spearman value: 79.948683747966 - type: euclidean_pearson value: 81.55702283757084 - type: euclidean_spearman value: 80.1721505114231 - type: manhattan_pearson value: 81.52251518619441 - type: manhattan_spearman value: 80.1469800135577 - task: type: STS dataset: type: mteb/sts15-sts name: MTEB STS15 config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 87.97170104226318 - type: cos_sim_spearman value: 88.82021731518206 - type: euclidean_pearson value: 87.92950547187615 - type: euclidean_spearman value: 88.67043634645866 - type: manhattan_pearson value: 87.90668112827639 - type: manhattan_spearman value: 88.64471082785317 - task: type: STS dataset: type: mteb/sts16-sts name: MTEB STS16 config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 83.02790375770599 - type: cos_sim_spearman value: 84.46308496590792 - type: euclidean_pearson value: 84.29430000414911 - type: euclidean_spearman value: 84.77298303589936 - type: manhattan_pearson value: 84.23919291368665 - type: manhattan_spearman value: 84.75272234871308 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-en) config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 87.62885108477064 - type: cos_sim_spearman value: 87.58456196391622 - type: euclidean_pearson value: 88.2602775281007 - type: euclidean_spearman value: 87.51556278299846 - type: manhattan_pearson value: 88.11224053672842 - type: manhattan_spearman value: 87.4336094383095 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (en) config: en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 63.98187965128411 - type: cos_sim_spearman value: 64.0653163219731 - type: euclidean_pearson value: 62.30616725924099 - type: euclidean_spearman value: 61.556971332295916 - type: manhattan_pearson value: 62.07642330128549 - type: manhattan_spearman value: 61.155494129828 - task: type: STS dataset: type: mteb/stsbenchmark-sts name: MTEB STSBenchmark config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 85.6089703921826 - type: cos_sim_spearman value: 86.52303197250791 - type: euclidean_pearson value: 85.95801955963246 - type: euclidean_spearman value: 86.25242424112962 - type: manhattan_pearson value: 85.88829100470312 - type: manhattan_spearman value: 86.18742955805165 - task: type: Reranking dataset: type: mteb/scidocs-reranking name: MTEB SciDocsRR config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 83.02282098487036 - type: mrr value: 95.05126409538174 - task: type: Retrieval dataset: type: scifact name: MTEB SciFact config: default split: test revision: None metrics: - type: map_at_1 value: 55.928 - type: map_at_10 value: 67.308 - type: map_at_100 value: 67.89500000000001 - type: map_at_1000 value: 67.91199999999999 - type: map_at_3 value: 65.091 - type: map_at_5 value: 66.412 - type: mrr_at_1 value: 58.667 - type: mrr_at_10 value: 68.401 - type: mrr_at_100 value: 68.804 - type: mrr_at_1000 value: 68.819 - type: mrr_at_3 value: 66.72200000000001 - type: mrr_at_5 value: 67.72200000000001 - type: ndcg_at_1 value: 58.667 - type: ndcg_at_10 value: 71.944 - type: ndcg_at_100 value: 74.464 - type: ndcg_at_1000 value: 74.82799999999999 - type: ndcg_at_3 value: 68.257 - type: ndcg_at_5 value: 70.10300000000001 - type: precision_at_1 value: 58.667 - type: precision_at_10 value: 9.533 - type: precision_at_100 value: 1.09 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 27.222 - type: precision_at_5 value: 17.533 - type: recall_at_1 value: 55.928 - type: recall_at_10 value: 84.65 - type: recall_at_100 value: 96.267 - type: recall_at_1000 value: 99 - type: recall_at_3 value: 74.656 - type: recall_at_5 value: 79.489 - task: type: PairClassification dataset: type: mteb/sprintduplicatequestions-pairclassification name: MTEB SprintDuplicateQuestions config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.79009900990098 - type: cos_sim_ap value: 94.5795129511524 - type: cos_sim_f1 value: 89.34673366834171 - type: cos_sim_precision value: 89.79797979797979 - type: cos_sim_recall value: 88.9 - type: dot_accuracy value: 99.53465346534654 - type: dot_ap value: 81.56492504352725 - type: dot_f1 value: 76.33816908454227 - type: dot_precision value: 76.37637637637637 - type: dot_recall value: 76.3 - type: euclidean_accuracy value: 99.78514851485149 - type: euclidean_ap value: 94.59134620408962 - type: euclidean_f1 value: 88.96484375 - type: euclidean_precision value: 86.92748091603053 - type: euclidean_recall value: 91.10000000000001 - type: manhattan_accuracy value: 99.78415841584159 - type: manhattan_ap value: 94.5190197328845 - type: manhattan_f1 value: 88.84462151394423 - type: manhattan_precision value: 88.4920634920635 - type: manhattan_recall value: 89.2 - type: max_accuracy value: 99.79009900990098 - type: max_ap value: 94.59134620408962 - type: max_f1 value: 89.34673366834171 - task: type: Clustering dataset: type: mteb/stackexchange-clustering name: MTEB StackExchangeClustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 65.1487505617497 - task: type: Clustering dataset: type: mteb/stackexchange-clustering-p2p name: MTEB StackExchangeClusteringP2P config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 32.502518166001856 - task: type: Reranking dataset: type: mteb/stackoverflowdupquestions-reranking name: MTEB StackOverflowDupQuestions config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 50.33775480236701 - type: mrr value: 51.17302223919871 - task: type: Summarization dataset: type: mteb/summeval name: MTEB SummEval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 30.561111309808208 - type: cos_sim_spearman value: 30.2839254379273 - type: dot_pearson value: 29.560242291401973 - type: dot_spearman value: 30.51527274679116 - task: type: Retrieval dataset: type: trec-covid name: MTEB TRECCOVID config: default split: test revision: None metrics: - type: map_at_1 value: 0.215 - type: map_at_10 value: 1.752 - type: map_at_100 value: 9.258 - type: map_at_1000 value: 23.438 - type: map_at_3 value: 0.6 - type: map_at_5 value: 0.968 - type: mrr_at_1 value: 84 - type: mrr_at_10 value: 91.333 - type: mrr_at_100 value: 91.333 - type: mrr_at_1000 value: 91.333 - type: mrr_at_3 value: 91.333 - type: mrr_at_5 value: 91.333 - type: ndcg_at_1 value: 75 - type: ndcg_at_10 value: 69.596 - type: ndcg_at_100 value: 51.970000000000006 - type: ndcg_at_1000 value: 48.864999999999995 - type: ndcg_at_3 value: 73.92699999999999 - type: ndcg_at_5 value: 73.175 - type: precision_at_1 value: 84 - type: precision_at_10 value: 74 - type: precision_at_100 value: 53.2 - type: precision_at_1000 value: 21.836 - type: precision_at_3 value: 79.333 - type: precision_at_5 value: 78.4 - type: recall_at_1 value: 0.215 - type: recall_at_10 value: 1.9609999999999999 - type: recall_at_100 value: 12.809999999999999 - type: recall_at_1000 value: 46.418 - type: recall_at_3 value: 0.6479999999999999 - type: recall_at_5 value: 1.057 - task: type: Retrieval dataset: type: webis-touche2020 name: MTEB Touche2020 config: default split: test revision: None metrics: - type: map_at_1 value: 3.066 - type: map_at_10 value: 10.508000000000001 - type: map_at_100 value: 16.258 - type: map_at_1000 value: 17.705000000000002 - type: map_at_3 value: 6.157 - type: map_at_5 value: 7.510999999999999 - type: mrr_at_1 value: 34.694 - type: mrr_at_10 value: 48.786 - type: mrr_at_100 value: 49.619 - type: mrr_at_1000 value: 49.619 - type: mrr_at_3 value: 45.918 - type: mrr_at_5 value: 46.837 - type: ndcg_at_1 value: 31.633 - type: ndcg_at_10 value: 26.401999999999997 - type: ndcg_at_100 value: 37.139 - type: ndcg_at_1000 value: 48.012 - type: ndcg_at_3 value: 31.875999999999998 - type: ndcg_at_5 value: 27.383000000000003 - type: precision_at_1 value: 34.694 - type: precision_at_10 value: 22.857 - type: precision_at_100 value: 7.611999999999999 - type: precision_at_1000 value: 1.492 - type: precision_at_3 value: 33.333 - type: precision_at_5 value: 26.122 - type: recall_at_1 value: 3.066 - type: recall_at_10 value: 16.239 - type: recall_at_100 value: 47.29 - type: recall_at_1000 value: 81.137 - type: recall_at_3 value: 7.069 - type: recall_at_5 value: 9.483 - task: type: Classification dataset: type: mteb/toxic_conversations_50k name: MTEB ToxicConversationsClassification config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 72.1126 - type: ap value: 14.710862719285753 - type: f1 value: 55.437808972378846 - task: type: Classification dataset: type: mteb/tweet_sentiment_extraction name: MTEB TweetSentimentExtractionClassification config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 60.39049235993209 - type: f1 value: 60.69810537250234 - task: type: Clustering dataset: type: mteb/twentynewsgroups-clustering name: MTEB TwentyNewsgroupsClustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 48.15576640316866 - task: type: PairClassification dataset: type: mteb/twittersemeval2015-pairclassification name: MTEB TwitterSemEval2015 config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 86.52917684925792 - type: cos_sim_ap value: 75.97497873817315 - type: cos_sim_f1 value: 70.01151926276718 - type: cos_sim_precision value: 67.98409147402435 - type: cos_sim_recall value: 72.16358839050132 - type: dot_accuracy value: 82.47004828038385 - type: dot_ap value: 62.48739894974198 - type: dot_f1 value: 59.13107511045656 - type: dot_precision value: 55.27765029830197 - type: dot_recall value: 63.562005277044854 - type: euclidean_accuracy value: 86.46361089586935 - type: euclidean_ap value: 75.59282886839452 - type: euclidean_f1 value: 69.6465443945099 - type: euclidean_precision value: 64.52847175331982 - type: euclidean_recall value: 75.64643799472296 - type: manhattan_accuracy value: 86.43380818978363 - type: manhattan_ap value: 75.5742420974403 - type: manhattan_f1 value: 69.8636926889715 - type: manhattan_precision value: 65.8644859813084 - type: manhattan_recall value: 74.37994722955145 - type: max_accuracy value: 86.52917684925792 - type: max_ap value: 75.97497873817315 - type: max_f1 value: 70.01151926276718 - task: type: PairClassification dataset: type: mteb/twitterurlcorpus-pairclassification name: MTEB TwitterURLCorpus config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 89.29056545193464 - type: cos_sim_ap value: 86.63028865482376 - type: cos_sim_f1 value: 79.18166458532285 - type: cos_sim_precision value: 75.70585756426465 - type: cos_sim_recall value: 82.99199260856174 - type: dot_accuracy value: 85.23305002522606 - type: dot_ap value: 76.0482687263196 - type: dot_f1 value: 70.80484330484332 - type: dot_precision value: 65.86933474688577 - type: dot_recall value: 76.53988296889437 - type: euclidean_accuracy value: 89.26145845461248 - type: euclidean_ap value: 86.54073288416006 - type: euclidean_f1 value: 78.9721371479794 - type: euclidean_precision value: 76.68649354417525 - type: euclidean_recall value: 81.39821373575609 - type: manhattan_accuracy value: 89.22847052431405 - type: manhattan_ap value: 86.51250729037905 - type: manhattan_f1 value: 78.94601825044894 - type: manhattan_precision value: 75.32694594027555 - type: manhattan_recall value: 82.93039728980598 - type: max_accuracy value: 89.29056545193464 - type: max_ap value: 86.63028865482376 - type: max_f1 value: 79.18166458532285 language: - en license: mit --- # E5-base-v2 [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://arxiv.org/pdf/2212.03533.pdf). Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022 This model has 12 layers and the embedding size is 768. ## Usage Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset. ```python import torch.nn.functional as F from torch import Tensor from transformers import AutoTokenizer, AutoModel def average_pool(last_hidden_states: Tensor, attention_mask: Tensor) -> Tensor: last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0) return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None] # Each input text should start with "query: " or "passage: ". # For tasks other than retrieval, you can simply use the "query: " prefix. input_texts = ['query: how much protein should a female eat', 'query: summit define', "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.", "passage: Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments."] tokenizer = AutoTokenizer.from_pretrained('intfloat/e5-base-v2') model = AutoModel.from_pretrained('intfloat/e5-base-v2') # Tokenize the input texts batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt') outputs = model(**batch_dict) embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask']) # normalize embeddings embeddings = F.normalize(embeddings, p=2, dim=1) scores = (embeddings[:2] @ embeddings[2:].T) * 100 print(scores.tolist()) ``` ## Training Details Please refer to our paper at [https://arxiv.org/pdf/2212.03533.pdf](https://arxiv.org/pdf/2212.03533.pdf). ## Benchmark Evaluation Check out [unilm/e5](https://github.com/microsoft/unilm/tree/master/e5) to reproduce evaluation results on the [BEIR](https://arxiv.org/abs/2104.08663) and [MTEB benchmark](https://arxiv.org/abs/2210.07316). ## Support for Sentence Transformers Below is an example for usage with sentence_transformers. ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer('intfloat/e5-base-v2') input_texts = [ 'query: how much protein should a female eat', 'query: summit define', "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.", "passage: Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments." ] embeddings = model.encode(input_texts, normalize_embeddings=True) ``` Package requirements `pip install sentence_transformers~=2.2.2` Contributors: [michaelfeil](https://huggingface.co/michaelfeil) ## FAQ **1. Do I need to add the prefix "query: " and "passage: " to input texts?** Yes, this is how the model is trained, otherwise you will see a performance degradation. Here are some rules of thumb: - Use "query: " and "passage: " correspondingly for asymmetric tasks such as passage retrieval in open QA, ad-hoc information retrieval. - Use "query: " prefix for symmetric tasks such as semantic similarity, paraphrase retrieval. - Use "query: " prefix if you want to use embeddings as features, such as linear probing classification, clustering. **2. Why are my reproduced results slightly different from reported in the model card?** Different versions of `transformers` and `pytorch` could cause negligible but non-zero performance differences. **3. Why does the cosine similarity scores distribute around 0.7 to 1.0?** This is a known and expected behavior as we use a low temperature 0.01 for InfoNCE contrastive loss. For text embedding tasks like text retrieval or semantic similarity, what matters is the relative order of the scores instead of the absolute values, so this should not be an issue. ## Citation If you find our paper or models helpful, please consider cite as follows: ``` @article{wang2022text, title={Text Embeddings by Weakly-Supervised Contrastive Pre-training}, author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu}, journal={arXiv preprint arXiv:2212.03533}, year={2022} } ``` ## Limitations This model only works for English texts. Long texts will be truncated to at most 512 tokens.

facebook/wav2vec2-xls-r-1b

facebook

transformers

--- language: - multilingual - ab - af - sq - am - ar - hy - as - az - ba - eu - be - bn - bs - br - bg - my - yue - ca - ceb - km - zh - cv - hr - cs - da - dv - nl - en - eo - et - fo - fi - fr - gl - lg - ka - de - el - gn - gu - ht - cnh - ha - haw - he - hi - hu - is - id - ia - ga - it - ja - jv - kb - kn - kk - rw - ky - ko - ku - lo - la - lv - ln - lt - lm - mk - mg - ms - ml - mt - gv - mi - mr - mn - ne - no - nn - oc - or - ps - fa - pl - pt - pa - ro - rm - rm - ru - sah - sa - sco - sr - sn - sd - si - sk - sl - so - hsb - es - su - sw - sv - tl - tg - ta - tt - te - th - bo - tp - tr - tk - uk - ur - uz - vi - vot - war - cy - yi - yo - zu language_bcp47: - zh-HK - zh-TW - fy-NL datasets: - common_voice - multilingual_librispeech tags: - speech - xls_r - xls_r_pretrained license: apache-2.0 --- # Wav2Vec2-XLS-R-1B [Facebook's Wav2Vec2 XLS-R](https://ai.facebook.com/blog/xls-r-self-supervised-speech-processing-for-128-languages) counting **1 billion** parameters.  XLS-R is Facebook AI's large-scale multilingual pretrained model for speech (the "XLM-R for Speech"). It is pretrained on 436k hours of unlabeled speech, including VoxPopuli, MLS, CommonVoice, BABEL, and VoxLingua107. It uses the wav2vec 2.0 objective, in 128 languages. When using the model make sure that your speech input is sampled at 16kHz. **Note**: This model should be fine-tuned on a downstream task, like Automatic Speech Recognition, Translation, or Classification. Check out [**this blog**](https://huggingface.co/blog/fine-tune-xlsr-wav2vec2) for more information about ASR. [XLS-R Paper](https://arxiv.org/abs/2111.09296) **Abstract** This paper presents XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. We train models with up to 2B parameters on 436K hours of publicly available speech audio in 128 languages, an order of magnitude more public data than the largest known prior work. Our evaluation covers a wide range of tasks, domains, data regimes and languages, both high and low-resource. On the CoVoST-2 speech translation benchmark, we improve the previous state of the art by an average of 7.4 BLEU over 21 translation directions into English. For speech recognition, XLS-R improves over the best known prior work on BABEL, MLS, CommonVoice as well as VoxPopuli, lowering error rates by 20%-33% relative on average. XLS-R also sets a new state of the art on VoxLingua107 language identification. Moreover, we show that with sufficient model size, cross-lingual pretraining can outperform English-only pretraining when translating English speech into other languages, a setting which favors monolingual pretraining. We hope XLS-R can help to improve speech processing tasks for many more languages of the world. The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20. # Usage See [this google colab](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/Fine_Tune_XLS_R_on_Common_Voice.ipynb) for more information on how to fine-tune the model. You can find other pretrained XLS-R models with different numbers of parameters: * [300M parameters version](https://huggingface.co/facebook/wav2vec2-xls-r-300m) * [1B version version](https://huggingface.co/facebook/wav2vec2-xls-r-1b) * [2B version version](https://huggingface.co/facebook/wav2vec2-xls-r-2b)

vinid/plip

vinid

transformers

zero-shot-image-classification

--- {} --- ## Model Use (from [CLIP Model Card](https://huggingface.co/openai/clip-vit-large-patch14)) ### Intended Use The model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. We also hope it can be used for interdisciplinary studies of the potential impact of such models - the CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis. #### Primary intended uses The primary intended users of these models are AI researchers. We primarily imagine the model will be used by researchers to better understand robustness, generalization, and other capabilities, biases, and constraints of computer vision models. ### Out-of-Scope Use Cases **Any** deployed use case of the model - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment, are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task specific testing especially given the variability of CLIP’s performance with different class taxonomies. This makes untested and unconstrained deployment of the model in any use case currently potentially harmful. Since the model has not been purposefully trained in or evaluated on any languages other than English, its use should be limited to English language use cases. # Disclaimer Please be advised that this function has been developed in compliance with the Twitter policy of data usage and sharing. It is important to note that the results obtained from this function are not intended to constitute medical advice or replace consultation with a qualified medical professional. The use of this function is solely at your own risk and should be consistent with applicable laws, regulations, and ethical considerations. We do not warrant or guarantee the accuracy, completeness, suitability, or usefulness of this function for any particular purpose, and we hereby disclaim any liability arising from any reliance placed on this function or any results obtained from its use. If you wish to review the original Twitter post, you should access the source page directly on Twitter.' # Privacy In accordance with the privacy and control policy of Twitter, we hereby declared that the data redistributed by us shall only comprise of Tweet IDs. The Tweet IDs will be employed to establish a linkage with the original Twitter post, as long as the original post is still accessible. The hyperlink will cease to function if the user deletes the original post. It is important to note that all tweets displayed on our service have already been classified as non-sensitive by Twitter. It is strictly prohibited to redistribute any content apart from the Tweet IDs. Any distribution carried out must adhere to the laws and regulations applicable in your jurisdiction, including export control laws and embargoes.'

Helsinki-NLP/opus-mt-en-zh

Helsinki-NLP

transformers

translation

--- language: - en - zh tags: - translation license: apache-2.0 --- ### eng-zho * source group: English * target group: Chinese * OPUS readme: [eng-zho](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-zho/README.md) * model: transformer * source language(s): eng * target language(s): cjy_Hans cjy_Hant cmn cmn_Hans cmn_Hant gan lzh lzh_Hans nan wuu yue yue_Hans yue_Hant * model: transformer * pre-processing: normalization + SentencePiece (spm32k,spm32k) * a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID) * download original weights: [opus-2020-07-17.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zho/opus-2020-07-17.zip) * test set translations: [opus-2020-07-17.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zho/opus-2020-07-17.test.txt) * test set scores: [opus-2020-07-17.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zho/opus-2020-07-17.eval.txt) ## Benchmarks | testset | BLEU | chr-F | |-----------------------|-------|-------| | Tatoeba-test.eng.zho | 31.4 | 0.268 | ### System Info: - hf_name: eng-zho - source_languages: eng - target_languages: zho - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-zho/README.md - original_repo: Tatoeba-Challenge - tags: ['translation'] - languages: ['en', 'zh'] - src_constituents: {'eng'} - tgt_constituents: {'cmn_Hans', 'nan', 'nan_Hani', 'gan', 'yue', 'cmn_Kana', 'yue_Hani', 'wuu_Bopo', 'cmn_Latn', 'yue_Hira', 'cmn_Hani', 'cjy_Hans', 'cmn', 'lzh_Hang', 'lzh_Hira', 'cmn_Hant', 'lzh_Bopo', 'zho', 'zho_Hans', 'zho_Hant', 'lzh_Hani', 'yue_Hang', 'wuu', 'yue_Kana', 'wuu_Latn', 'yue_Bopo', 'cjy_Hant', 'yue_Hans', 'lzh', 'cmn_Hira', 'lzh_Yiii', 'lzh_Hans', 'cmn_Bopo', 'cmn_Hang', 'hak_Hani', 'cmn_Yiii', 'yue_Hant', 'lzh_Kana', 'wuu_Hani'} - src_multilingual: False - tgt_multilingual: False - prepro: normalization + SentencePiece (spm32k,spm32k) - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zho/opus-2020-07-17.zip - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zho/opus-2020-07-17.test.txt - src_alpha3: eng - tgt_alpha3: zho - short_pair: en-zh - chrF2_score: 0.268 - bleu: 31.4 - brevity_penalty: 0.8959999999999999 - ref_len: 110468.0 - src_name: English - tgt_name: Chinese - train_date: 2020-07-17 - src_alpha2: en - tgt_alpha2: zh - prefer_old: False - long_pair: eng-zho - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535 - transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b - port_machine: brutasse - port_time: 2020-08-21-14:41

timm/efficientnet_b0.ra_in1k

timm

timm

image-classification

--- tags: - image-classification - timm library_name: timm license: apache-2.0 datasets: - imagenet-1k --- # Model card for efficientnet_b0.ra_in1k A EfficientNet image classification model. Trained on ImageNet-1k in `timm` using recipe template described below. Recipe details: * RandAugment `RA` recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as `B` recipe in [ResNet Strikes Back](https://arxiv.org/abs/2110.00476). * RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging * Step (exponential decay w/ staircase) LR schedule with warmup ## Model Details - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 5.3 - GMACs: 0.4 - Activations (M): 6.7 - Image size: 224 x 224 - **Papers:** - EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946 - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - **Dataset:** ImageNet-1k - **Original:** https://github.com/huggingface/pytorch-image-models ## Model Usage ### Image Classification ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model('efficientnet_b0.ra_in1k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5) ``` ### Feature Map Extraction ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'efficientnet_b0.ra_in1k', pretrained=True, features_only=True, ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 for o in output: # print shape of each feature map in output # e.g.: # torch.Size([1, 16, 112, 112]) # torch.Size([1, 24, 56, 56]) # torch.Size([1, 40, 28, 28]) # torch.Size([1, 112, 14, 14]) # torch.Size([1, 320, 7, 7]) print(o.shape) ``` ### Image Embeddings ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'efficientnet_b0.ra_in1k', pretrained=True, num_classes=0, # remove classifier nn.Linear ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 1280, 7, 7) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor ``` ## Model Comparison Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results). ## Citation ```bibtex @inproceedings{tan2019efficientnet, title={Efficientnet: Rethinking model scaling for convolutional neural networks}, author={Tan, Mingxing and Le, Quoc}, booktitle={International conference on machine learning}, pages={6105--6114}, year={2019}, organization={PMLR} } ``` ```bibtex @misc{rw2019timm, author = {Ross Wightman}, title = {PyTorch Image Models}, year = {2019}, publisher = {GitHub}, journal = {GitHub repository}, doi = {10.5281/zenodo.4414861}, howpublished = {\url{https://github.com/huggingface/pytorch-image-models}} } ``` ```bibtex @inproceedings{wightman2021resnet, title={ResNet strikes back: An improved training procedure in timm}, author={Wightman, Ross and Touvron, Hugo and Jegou, Herve}, booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future} } ```

hfl/chinese-bert-wwm-ext

hfl

transformers

fill-mask

--- language: - zh license: "apache-2.0" --- ## Chinese BERT with Whole Word Masking For further accelerating Chinese natural language processing, we provide **Chinese pre-trained BERT with Whole Word Masking**. **[Pre-Training with Whole Word Masking for Chinese BERT](https://arxiv.org/abs/1906.08101)** Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Ziqing Yang, Shijin Wang, Guoping Hu This repository is developed based on：https://github.com/google-research/bert You may also interested in, - Chinese BERT series: https://github.com/ymcui/Chinese-BERT-wwm - Chinese MacBERT: https://github.com/ymcui/MacBERT - Chinese ELECTRA: https://github.com/ymcui/Chinese-ELECTRA - Chinese XLNet: https://github.com/ymcui/Chinese-XLNet - Knowledge Distillation Toolkit - TextBrewer: https://github.com/airaria/TextBrewer More resources by HFL: https://github.com/ymcui/HFL-Anthology ## Citation If you find the technical report or resource is useful, please cite the following technical report in your paper. - Primary: https://arxiv.org/abs/2004.13922 ``` @inproceedings{cui-etal-2020-revisiting, title = "Revisiting Pre-Trained Models for {C}hinese Natural Language Processing", author = "Cui, Yiming and Che, Wanxiang and Liu, Ting and Qin, Bing and Wang, Shijin and Hu, Guoping", booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/2020.findings-emnlp.58", pages = "657--668", } ``` - Secondary: https://arxiv.org/abs/1906.08101 ``` @article{chinese-bert-wwm, title={Pre-Training with Whole Word Masking for Chinese BERT}, author={Cui, Yiming and Che, Wanxiang and Liu, Ting and Qin, Bing and Yang, Ziqing and Wang, Shijin and Hu, Guoping}, journal={arXiv preprint arXiv:1906.08101}, year={2019} } ```

facebook/sam-vit-base

facebook

transformers

mask-generation

--- license: apache-2.0 tags: - vision --- # Model Card for Segment Anything Model (SAM) - ViT Base (ViT-B) version <p> <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/sam-architecture.png" alt="Model architecture"> <em> Detailed architecture of Segment Anything Model (SAM).</em> </p> # Table of Contents 0. [TL;DR](#TL;DR) 1. [Model Details](#model-details) 2. [Usage](#usage) 3. [Citation](#citation) # TL;DR [Link to original repository](https://github.com/facebookresearch/segment-anything) | <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/sam-beancans.png" alt="Snow" width="600" height="600"> | <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/sam-dog-masks.png" alt="Forest" width="600" height="600"> | <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/sam-car-seg.png" alt="Mountains" width="600" height="600"> | |---------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------| The **Segment Anything Model (SAM)** produces high quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image. It has been trained on a [dataset](https://segment-anything.com/dataset/index.html) of 11 million images and 1.1 billion masks, and has strong zero-shot performance on a variety of segmentation tasks. The abstract of the paper states: > We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy respecting images. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks. We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive -- often competitive with or even superior to prior fully supervised results. We are releasing the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images at [https://segment-anything.com](https://segment-anything.com) to foster research into foundation models for computer vision. **Disclaimer**: Content from **this** model card has been written by the Hugging Face team, and parts of it were copy pasted from the original [SAM model card](https://github.com/facebookresearch/segment-anything). # Model Details The SAM model is made up of 3 modules: - The `VisionEncoder`: a VIT based image encoder. It computes the image embeddings using attention on patches of the image. Relative Positional Embedding is used. - The `PromptEncoder`: generates embeddings for points and bounding boxes - The `MaskDecoder`: a two-ways transformer which performs cross attention between the image embedding and the point embeddings (->) and between the point embeddings and the image embeddings. The outputs are fed - The `Neck`: predicts the output masks based on the contextualized masks produced by the `MaskDecoder`. # Usage ## Prompted-Mask-Generation ```python from PIL import Image import requests from transformers import SamModel, SamProcessor model = SamModel.from_pretrained("facebook/sam-vit-base") processor = SamProcessor.from_pretrained("facebook/sam-vit-base") img_url = "https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png" raw_image = Image.open(requests.get(img_url, stream=True).raw).convert("RGB") input_points = [[[450, 600]]] # 2D localization of a window ``` ```python inputs = processor(raw_image, input_points=input_points, return_tensors="pt").to("cuda") outputs = model(**inputs) masks = processor.image_processor.post_process_masks(outputs.pred_masks.cpu(), inputs["original_sizes"].cpu(), inputs["reshaped_input_sizes"].cpu()) scores = outputs.iou_scores ``` Among other arguments to generate masks, you can pass 2D locations on the approximate position of your object of interest, a bounding box wrapping the object of interest (the format should be x, y coordinate of the top right and bottom left point of the bounding box), a segmentation mask. At this time of writing, passing a text as input is not supported by the official model according to [the official repository](https://github.com/facebookresearch/segment-anything/issues/4#issuecomment-1497626844). For more details, refer to this notebook, which shows a walk throught of how to use the model, with a visual example! ## Automatic-Mask-Generation The model can be used for generating segmentation masks in a "zero-shot" fashion, given an input image. The model is automatically prompt with a grid of `1024` points which are all fed to the model. The pipeline is made for automatic mask generation. The following snippet demonstrates how easy you can run it (on any device! Simply feed the appropriate `points_per_batch` argument) ```python from transformers import pipeline generator = pipeline("mask-generation", device = 0, points_per_batch = 256) image_url = "https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png" outputs = generator(image_url, points_per_batch = 256) ``` Now to display the image: ```python import matplotlib.pyplot as plt from PIL import Image import numpy as np def show_mask(mask, ax, random_color=False): if random_color: color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0) else: color = np.array([30 / 255, 144 / 255, 255 / 255, 0.6]) h, w = mask.shape[-2:] mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1) ax.imshow(mask_image) plt.imshow(np.array(raw_image)) ax = plt.gca() for mask in outputs["masks"]: show_mask(mask, ax=ax, random_color=True) plt.axis("off") plt.show() ``` # Citation If you use this model, please use the following BibTeX entry. ``` @article{kirillov2023segany, title={Segment Anything}, author={Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and Whitehead, Spencer and Berg, Alexander C. and Lo, Wan-Yen and Doll{\'a}r, Piotr and Girshick, Ross}, journal={arXiv:2304.02643}, year={2023} } ```

cointegrated/rubert-tiny2

cointegrated

sentence-transformers

sentence-similarity

--- language: - ru pipeline_tag: sentence-similarity tags: - russian - fill-mask - pretraining - embeddings - masked-lm - tiny - feature-extraction - sentence-similarity - sentence-transformers - transformers license: mit widget: - text: Миниатюрная модель для [MASK] разных задач. --- This is an updated version of [cointegrated/rubert-tiny](https://huggingface.co/cointegrated/rubert-tiny): a small Russian BERT-based encoder with high-quality sentence embeddings. This [post in Russian](https://habr.com/ru/post/669674/) gives more details. The differences from the previous version include: - a larger vocabulary: 83828 tokens instead of 29564; - larger supported sequences: 2048 instead of 512; - sentence embeddings approximate LaBSE closer than before; - meaningful segment embeddings (tuned on the NLI task) - the model is focused only on Russian. The model should be used as is to produce sentence embeddings (e.g. for KNN classification of short texts) or fine-tuned for a downstream task. Sentence embeddings can be produced as follows: ```python # pip install transformers sentencepiece import torch from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("cointegrated/rubert-tiny2") model = AutoModel.from_pretrained("cointegrated/rubert-tiny2") # model.cuda() # uncomment it if you have a GPU def embed_bert_cls(text, model, tokenizer): t = tokenizer(text, padding=True, truncation=True, return_tensors='pt') with torch.no_grad(): model_output = model(**{k: v.to(model.device) for k, v in t.items()}) embeddings = model_output.last_hidden_state[:, 0, :] embeddings = torch.nn.functional.normalize(embeddings) return embeddings[0].cpu().numpy() print(embed_bert_cls('привет мир', model, tokenizer).shape) # (312,) ``` Alternatively, you can use the model with `sentence_transformers`: ```Python from sentence_transformers import SentenceTransformer model = SentenceTransformer('cointegrated/rubert-tiny2') sentences = ["привет мир", "hello world", "здравствуй вселенная"] embeddings = model.encode(sentences) print(embeddings) ```

openai-community/gpt2-large

openai-community

transformers

text-generation

--- language: en license: mit --- # GPT-2 Large ## Table of Contents - [Model Details](#model-details) - [How To Get Started With the Model](#how-to-get-started-with-the-model) - [Uses](#uses) - [Risks, Limitations and Biases](#risks-limitations-and-biases) - [Training](#training) - [Evaluation](#evaluation) - [Environmental Impact](#environmental-impact) - [Technical Specifications](#technical-specifications) - [Citation Information](#citation-information) - [Model Card Authors](#model-card-author) ## Model Details **Model Description:** GPT-2 Large is the **774M parameter** version of GPT-2, a transformer-based language model created and released by OpenAI. The model is a pretrained model on English language using a causal language modeling (CLM) objective. - **Developed by:** OpenAI, see [associated research paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) and [GitHub repo](https://github.com/openai/gpt-2) for model developers. - **Model Type:** Transformer-based language model - **Language(s):** English - **License:** [Modified MIT License](https://github.com/openai/gpt-2/blob/master/LICENSE) - **Related Models:** [GPT-2](https://huggingface.co/gpt2), [GPT-Medium](https://huggingface.co/gpt2-medium) and [GPT-XL](https://huggingface.co/gpt2-xl) - **Resources for more information:** - [Research Paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) - [OpenAI Blog Post](https://openai.com/blog/better-language-models/) - [GitHub Repo](https://github.com/openai/gpt-2) - [OpenAI Model Card for GPT-2](https://github.com/openai/gpt-2/blob/master/model_card.md) - Test the full generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large ## How to Get Started with the Model Use the code below to get started with the model. You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we set a seed for reproducibility: ```python >>> from transformers import pipeline, set_seed >>> generator = pipeline('text-generation', model='gpt2-large') >>> set_seed(42) >>> generator("Hello, I'm a language model,", max_length=30, num_return_sequences=5) [{'generated_text': "Hello, I'm a language model, I can do language modeling. In fact, this is one of the reasons I use languages. To get a"}, {'generated_text': "Hello, I'm a language model, which in its turn implements a model of how a human can reason about a language, and is in turn an"}, {'generated_text': "Hello, I'm a language model, why does this matter for you?\n\nWhen I hear new languages, I tend to start thinking in terms"}, {'generated_text': "Hello, I'm a language model, a functional language...\n\nI don't need to know anything else. If I want to understand about how"}, {'generated_text': "Hello, I'm a language model, not a toolbox.\n\nIn a nutshell, a language model is a set of attributes that define how"}] ``` Here is how to use this model to get the features of a given text in PyTorch: ```python from transformers import GPT2Tokenizer, GPT2Model tokenizer = GPT2Tokenizer.from_pretrained('gpt2-large') model = GPT2Model.from_pretrained('gpt2-large') text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='pt') output = model(**encoded_input) ``` and in TensorFlow: ```python from transformers import GPT2Tokenizer, TFGPT2Model tokenizer = GPT2Tokenizer.from_pretrained('gpt2-large') model = TFGPT2Model.from_pretrained('gpt2-large') text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='tf') output = model(encoded_input) ``` ## Uses #### Direct Use In their [model card about GPT-2](https://github.com/openai/gpt-2/blob/master/model_card.md), OpenAI wrote: > The primary intended users of these models are AI researchers and practitioners. > > We primarily imagine these language models will be used by researchers to better understand the behaviors, capabilities, biases, and constraints of large-scale generative language models. #### Downstream Use In their [model card about GPT-2](https://github.com/openai/gpt-2/blob/master/model_card.md), OpenAI wrote: > Here are some secondary use cases we believe are likely: > > - Writing assistance: Grammar assistance, autocompletion (for normal prose or code) > - Creative writing and art: exploring the generation of creative, fictional texts; aiding creation of poetry and other literary art. > - Entertainment: Creation of games, chat bots, and amusing generations. #### Misuse and Out-of-scope Use In their [model card about GPT-2](https://github.com/openai/gpt-2/blob/master/model_card.md), OpenAI wrote: > Because large-scale language models like GPT-2 do not distinguish fact from fiction, we don’t support use-cases that require the generated text to be true. > > Additionally, language models like GPT-2 reflect the biases inherent to the systems they were trained on, so we do not recommend that they be deployed into systems that interact with humans unless the deployers first carry out a study of biases relevant to the intended use-case. We found no statistically significant difference in gender, race, and religious bias probes between 774M and 1.5B, implying all versions of GPT-2 should be approached with similar levels of caution around use cases that are sensitive to biases around human attributes. ## Risks, Limitations and Biases **CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propogate historical and current stereotypes.** Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). The training data used for this model has not been released as a dataset one can browse. We know it contains a lot of unfiltered content from the internet, which is far from neutral. Predictions generated by the model can include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups. For example: ```python >>> from transformers import pipeline, set_seed >>> generator = pipeline('text-generation', model='gpt2-large') >>> set_seed(42) >>> generator("The man worked as a", max_length=10, num_return_sequences=5) [{'generated_text': 'The man worked as a security guard in a hotel'}, {'generated_text': 'The man worked as a salesman in Mexico and in'}, {'generated_text': 'The man worked as a supervisor at the warehouse for'}, {'generated_text': "The man worked as a cleaner for the store's"}, {'generated_text': 'The man worked as a barbershop apprentice.'}] >>> set_seed(42) >>> generator("The woman worked as a", max_length=10, num_return_sequences=5) [{'generated_text': 'The woman worked as a clerk at the bank.'}, {'generated_text': 'The woman worked as a caregiver, and her'}, {'generated_text': 'The woman worked as a customer service agent for a'}, {'generated_text': 'The woman worked as a cleaner at the store,'}, {'generated_text': 'The woman worked as a barista and was "'}] ``` This bias will also affect all fine-tuned versions of this model. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. ## Training #### Training Data The OpenAI team wanted to train this model on a corpus as large as possible. To build it, they scraped all the web pages from outbound links on Reddit which received at least 3 karma. Note that all Wikipedia pages were removed from this dataset, so the model was not trained on any part of Wikipedia. The resulting dataset (called WebText) weights 40GB of texts but has not been publicly released. You can find a list of the top 1,000 domains present in WebText [here](https://github.com/openai/gpt-2/blob/master/domains.txt). #### Training Procedure The model is pretrained on a very large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was trained to guess the next word in sentences. More precisely, inputs are sequences of continuous text of a certain length and the targets are the same sequence, shifted one token (word or piece of word) to the right. The model uses internally a mask-mechanism to make sure the predictions for the token `i` only uses the inputs from `1` to `i` but not the future tokens. This way, the model learns an inner representation of the English language that can then be used to extract features useful for downstream tasks. The texts are tokenized using a byte-level version of Byte Pair Encoding (BPE) (for unicode characters) and a vocabulary size of 50,257. The inputs are sequences of 1024 consecutive tokens. ## Evaluation The following evaluation information is extracted from the [associated paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf). #### Testing Data, Factors and Metrics The model authors write in the [associated paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) that: > Since our model operates on a byte level and does not require lossy pre-processing or tokenization, we can evaluate it on any language model benchmark. Results on language modeling datasets are commonly reported in a quantity which is a scaled or ex- ponentiated version of the average negative log probability per canonical prediction unit - usually a character, a byte, or a word. We evaluate the same quantity by computing the log-probability of a dataset according to a WebText LM and dividing by the number of canonical units. For many of these datasets, WebText LMs would be tested significantly out- of-distribution, having to predict aggressively standardized text, tokenization artifacts such as disconnected punctuation and contractions, shuffled sentences, and even the string <UNK> which is extremely rare in WebText - occurring only 26 times in 40 billion bytes. We report our main results...using invertible de-tokenizers which remove as many of these tokenization / pre-processing artifacts as possible. Since these de-tokenizers are invertible, we can still calculate the log probability of a dataset and they can be thought of as a simple form of domain adaptation. #### Results The model achieves the following results without any fine-tuning (zero-shot): | Dataset | LAMBADA | LAMBADA | CBT-CN | CBT-NE | WikiText2 | PTB | enwiki8 | text8 | WikiText103 | 1BW | |:--------:|:-------:|:-------:|:------:|:------:|:---------:|:------:|:-------:|:------:|:-----------:|:-----:| | (metric) | (PPL) | (ACC) | (ACC) | (ACC) | (PPL) | (PPL) | (BPB) | (BPC) | (PPL) | (PPL) | | | 10.87 | 60.12 | 93.45 | 88.0 | 19.93 | 40.31 | 0.97 | 1.02 | 22.05 | 44.575| ## Environmental Impact Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** Unknown - **Hours used:** Unknown - **Cloud Provider:** Unknown - **Compute Region:** Unknown - **Carbon Emitted:** Unknown ## Technical Specifications See the [associated paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) for details on the modeling architecture, objective, compute infrastructure, and training details. ## Citation Information ```bibtex @article{radford2019language, title={Language models are unsupervised multitask learners}, author={Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya and others}, journal={OpenAI blog}, volume={1}, number={8}, pages={9}, year={2019} } ``` ## Model Card Authors This model card was written by the Hugging Face team.