Datasets:

librarian-bots

/

dataset_cards_with_metadata

like 11

Follow

Librarian Bots 59

ferrazzipietro/LS_Llama-3.1-8B_e3c-sentences-sk-unrevised_NoQuant_64_32_0.01_64_BestF1_en

ferrazzipietro

--- dataset_info: features: - name: sentence dtype: string - name: entities list: - name: id dtype: string - name: offsets sequence: int64 - name: role dtype: string - name: semantic_type_id dtype: string - name: text dtype: string - name: type dtype: string - name: original_text dtype: string - name: original_id dtype: string - name: tokens sequence: string - name: ner_tags sequence: int64 - name: ground_truth_word_level sequence: string - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: labels sequence: int64 - name: predictions sequence: string - name: ground_truth_labels sequence: string splits: - name: all_validation num_bytes: 418249 num_examples: 106 - name: test num_bytes: 2472788 num_examples: 666 download_size: 292641 dataset_size: 2891037 configs: - config_name: default data_files: - split: all_validation path: data/all_validation-* - split: test path: data/test-* ---

ferrazzipietro/LS_Llama-3.1-8B_e3c-sentences-sk-unrevised_NoQuant_32_32_0.05_64_BestF1_en

ferrazzipietro

--- dataset_info: features: - name: sentence dtype: string - name: entities list: - name: id dtype: string - name: offsets sequence: int64 - name: role dtype: string - name: semantic_type_id dtype: string - name: text dtype: string - name: type dtype: string - name: original_text dtype: string - name: original_id dtype: string - name: tokens sequence: string - name: ner_tags sequence: int64 - name: ground_truth_word_level sequence: string - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: labels sequence: int64 - name: predictions sequence: string - name: ground_truth_labels sequence: string splits: - name: all_validation num_bytes: 418249 num_examples: 106 - name: test num_bytes: 2472788 num_examples: 666 download_size: 292535 dataset_size: 2891037 configs: - config_name: default data_files: - split: all_validation path: data/all_validation-* - split: test path: data/test-* ---

ferrazzipietro/LS_Llama-3.1-8B_e3c-sentences-sk-unrevised_NoQuant_16_32_0.01_64_BestF1_en

ferrazzipietro

--- dataset_info: features: - name: sentence dtype: string - name: entities list: - name: id dtype: string - name: offsets sequence: int64 - name: role dtype: string - name: semantic_type_id dtype: string - name: text dtype: string - name: type dtype: string - name: original_text dtype: string - name: original_id dtype: string - name: tokens sequence: string - name: ner_tags sequence: int64 - name: ground_truth_word_level sequence: string - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: labels sequence: int64 - name: predictions sequence: string - name: ground_truth_labels sequence: string splits: - name: all_validation num_bytes: 418249 num_examples: 106 - name: test num_bytes: 2472788 num_examples: 666 download_size: 292434 dataset_size: 2891037 configs: - config_name: default data_files: - split: all_validation path: data/all_validation-* - split: test path: data/test-* ---

ferrazzipietro/LS_Llama-3.1-8B_e3c-sentences-sk-unrevised_NoQuant_64_64_0.05_64_BestF1_en

ferrazzipietro

--- dataset_info: features: - name: sentence dtype: string - name: entities list: - name: id dtype: string - name: offsets sequence: int64 - name: role dtype: string - name: semantic_type_id dtype: string - name: text dtype: string - name: type dtype: string - name: original_text dtype: string - name: original_id dtype: string - name: tokens sequence: string - name: ner_tags sequence: int64 - name: ground_truth_word_level sequence: string - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: labels sequence: int64 - name: predictions sequence: string - name: ground_truth_labels sequence: string splits: - name: all_validation num_bytes: 418249 num_examples: 106 - name: test num_bytes: 2472788 num_examples: 666 download_size: 292636 dataset_size: 2891037 configs: - config_name: default data_files: - split: all_validation path: data/all_validation-* - split: test path: data/test-* ---

ferrazzipietro/LS_Llama-3.1-8B_e3c-sentences-sk-unrevised_NoQuant_32_64_0.05_64_BestF1_en

ferrazzipietro

--- dataset_info: features: - name: sentence dtype: string - name: entities list: - name: id dtype: string - name: offsets sequence: int64 - name: role dtype: string - name: semantic_type_id dtype: string - name: text dtype: string - name: type dtype: string - name: original_text dtype: string - name: original_id dtype: string - name: tokens sequence: string - name: ner_tags sequence: int64 - name: ground_truth_word_level sequence: string - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: labels sequence: int64 - name: predictions sequence: string - name: ground_truth_labels sequence: string splits: - name: all_validation num_bytes: 418249 num_examples: 106 - name: test num_bytes: 2472788 num_examples: 666 download_size: 292687 dataset_size: 2891037 configs: - config_name: default data_files: - split: all_validation path: data/all_validation-* - split: test path: data/test-* ---

ferrazzipietro/LS_Llama-3.1-8B_e3c-sentences-sk-unrevised_NoQuant_16_16_0.01_64_BestF1_en

ferrazzipietro

--- dataset_info: features: - name: sentence dtype: string - name: entities list: - name: id dtype: string - name: offsets sequence: int64 - name: role dtype: string - name: semantic_type_id dtype: string - name: text dtype: string - name: type dtype: string - name: original_text dtype: string - name: original_id dtype: string - name: tokens sequence: string - name: ner_tags sequence: int64 - name: ground_truth_word_level sequence: string - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: labels sequence: int64 - name: predictions sequence: string - name: ground_truth_labels sequence: string splits: - name: all_validation num_bytes: 418249 num_examples: 106 - name: test num_bytes: 2472788 num_examples: 666 download_size: 293274 dataset_size: 2891037 configs: - config_name: default data_files: - split: all_validation path: data/all_validation-* - split: test path: data/test-* ---

ferrazzipietro/LS_Llama-3.1-8B_e3c-sentences-sk-unrevised_NoQuant_64_16_0.01_64_BestF1_en

ferrazzipietro

--- dataset_info: features: - name: sentence dtype: string - name: entities list: - name: id dtype: string - name: offsets sequence: int64 - name: role dtype: string - name: semantic_type_id dtype: string - name: text dtype: string - name: type dtype: string - name: original_text dtype: string - name: original_id dtype: string - name: tokens sequence: string - name: ner_tags sequence: int64 - name: ground_truth_word_level sequence: string - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: labels sequence: int64 - name: predictions sequence: string - name: ground_truth_labels sequence: string splits: - name: all_validation num_bytes: 418249 num_examples: 106 - name: test num_bytes: 2472788 num_examples: 666 download_size: 292885 dataset_size: 2891037 configs: - config_name: default data_files: - split: all_validation path: data/all_validation-* - split: test path: data/test-* ---

ferrazzipietro/LS_Llama-3.1-8B_e3c-sentences-sk-unrevised_NoQuant_16_32_0.05_64_BestF1_en

ferrazzipietro

--- dataset_info: features: - name: sentence dtype: string - name: entities list: - name: id dtype: string - name: offsets sequence: int64 - name: role dtype: string - name: semantic_type_id dtype: string - name: text dtype: string - name: type dtype: string - name: original_text dtype: string - name: original_id dtype: string - name: tokens sequence: string - name: ner_tags sequence: int64 - name: ground_truth_word_level sequence: string - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: labels sequence: int64 - name: predictions sequence: string - name: ground_truth_labels sequence: string splits: - name: all_validation num_bytes: 418249 num_examples: 106 - name: test num_bytes: 2472788 num_examples: 666 download_size: 292523 dataset_size: 2891037 configs: - config_name: default data_files: - split: all_validation path: data/all_validation-* - split: test path: data/test-* ---

ferrazzipietro/LS_Llama-3.1-8B_e3c-sentences-sk-unrevised_NoQuant_64_16_0.05_64_BestF1_en

ferrazzipietro

--- dataset_info: features: - name: sentence dtype: string - name: entities list: - name: id dtype: string - name: offsets sequence: int64 - name: role dtype: string - name: semantic_type_id dtype: string - name: text dtype: string - name: type dtype: string - name: original_text dtype: string - name: original_id dtype: string - name: tokens sequence: string - name: ner_tags sequence: int64 - name: ground_truth_word_level sequence: string - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: labels sequence: int64 - name: predictions sequence: string - name: ground_truth_labels sequence: string splits: - name: all_validation num_bytes: 418249 num_examples: 106 - name: test num_bytes: 2472788 num_examples: 666 download_size: 292738 dataset_size: 2891037 configs: - config_name: default data_files: - split: all_validation path: data/all_validation-* - split: test path: data/test-* ---

sartifyllc/sft_question_answer_gemma_test

sartifyllc

--- dataset_info: features: - name: instruction dtype: string - name: response dtype: string splits: - name: train num_bytes: 12356 num_examples: 50 download_size: 9559 dataset_size: 12356 configs: - config_name: default data_files: - split: train path: data/train-* ---

juliadollis/stf_regex_ner_completo_80

juliadollis

--- dataset_info: features: - name: inteiro_teor dtype: string - name: url_download dtype: string - name: dataDecisao dtype: timestamp[ns] - name: dataPublicacao dtype: timestamp[ns] - name: decisao dtype: string - name: descricaoClasse dtype: string - name: ementa dtype: string - name: id dtype: string - name: jurisprudenciaCitada dtype: string - name: ministroRelator dtype: string - name: nomeOrgaoJulgador dtype: string - name: numeroProcesso dtype: string - name: referenciasLegislativas sequence: string - name: siglaClasse dtype: string - name: tipoDeDecisao dtype: string - name: titulo dtype: string - name: acordaosSimilares sequence: string - name: partes_lista_texto dtype: string - name: temaProcs sequence: string - name: inteiro_teor_regex dtype: string - name: NER struct: - name: JURISPRUDENCIA sequence: string - name: LEGISLACAO sequence: string - name: LOCAL sequence: string - name: ORGANIZACAO sequence: string - name: PESSOA sequence: string - name: TEMPO sequence: string - name: desambiguacao list: - name: class dtype: string - name: count dtype: int64 - name: elements sequence: string - name: entity dtype: string splits: - name: train num_bytes: 9037862346 num_examples: 78477 download_size: 2459050799 dataset_size: 9037862346 configs: - config_name: default data_files: - split: train path: data/train-* ---

mlfoundations-dev/airoboros_stage_3_coding_none_response_gpt-4o-inst_gpt_4o-mini_resp_test

mlfoundations-dev

--- dataset_info: features: - name: instruction dtype: string - name: response dtype: string - name: airoboros_subset dtype: string splits: - name: train num_bytes: 3754298 num_examples: 1200 download_size: 1765579 dataset_size: 3754298 configs: - config_name: default data_files: - split: train path: data/train-* ---

mathreward/data_collection_8b_math_2

mathreward

--- dataset_info: features: - name: idx dtype: int64 - name: gt dtype: string - name: my_solu dtype: string splits: - name: train num_bytes: 3283996207 num_examples: 607500 download_size: 1342872050 dataset_size: 3283996207 configs: - config_name: default data_files: - split: train path: data/train-* ---

makcedward/openai-moderation

makcedward

--- dataset_info: features: - name: prompt dtype: string - name: S dtype: float64 - name: H dtype: float64 - name: V dtype: float64 - name: HR dtype: float64 - name: SH dtype: float64 - name: S3 dtype: float64 - name: H2 dtype: float64 - name: V2 dtype: float64 splits: - name: test num_bytes: 1222579 num_examples: 1680 download_size: 746347 dataset_size: 1222579 configs: - config_name: default data_files: - split: test path: data/test-* task_categories: - text-classification language: - en tags: - prompt_guard - prmopt - LlamaGuard --- # Dataset Homepage: https://github.com/openai/moderation-api-release Description: A Holistic Approach to Undesired Content Detection Citation: ``` @article{openai2022moderation, title={A Holistic Approach to Undesired Content Detection}, author={Todor Markov and Chong Zhang and Sandhini Agarwal and Tyna Eloundou and Teddy Lee and Steven Adler and Angela Jiang and Lilian Weng}, journal={arXiv preprint arXiv:2208.03274}, year={2022} } ```

JimmieJom/boofu

JimmieJom

--- license: apache-2.0 ---

pclucas14/nqa-RAG-256_22_24

pclucas14

--- dataset_info: features: - name: text sequence: sequence: string - name: questions sequence: string - name: answers sequence: sequence: string - name: document_id dtype: string - name: split dtype: string splits: - name: train num_bytes: 26388567 num_examples: 65 download_size: 10775611 dataset_size: 26388567 configs: - config_name: default data_files: - split: train path: data/train-* ---

bustamiyusoef/TransTigriya-English

bustamiyusoef

--- task_categories: - translation language: - ti - en --- The original data from [HornMT](https://github.com/asmelashteka/HornMT/tree/main)

pclucas14/nqa-RAG-256_5_24

pclucas14

--- dataset_info: features: - name: text sequence: sequence: string - name: questions sequence: string - name: answers sequence: sequence: string - name: document_id dtype: string - name: split dtype: string splits: - name: train num_bytes: 26742364 num_examples: 66 download_size: 10694928 dataset_size: 26742364 configs: - config_name: default data_files: - split: train path: data/train-* ---

pclucas14/nqa-RAG-256_21_24

pclucas14

--- dataset_info: features: - name: text sequence: sequence: string - name: questions sequence: string - name: answers sequence: sequence: string - name: document_id dtype: string - name: split dtype: string splits: - name: train num_bytes: 25139427 num_examples: 65 download_size: 10600443 dataset_size: 25139427 configs: - config_name: default data_files: - split: train path: data/train-* ---

pclucas14/nqa-RAG-256_23_24

pclucas14

--- dataset_info: features: - name: text sequence: sequence: string - name: questions sequence: string - name: answers sequence: sequence: string - name: document_id dtype: string - name: split dtype: string splits: - name: train num_bytes: 26073886 num_examples: 65 download_size: 11091963 dataset_size: 26073886 configs: - config_name: default data_files: - split: train path: data/train-* ---

pclucas14/nqa-RAG-256_20_24

pclucas14

--- dataset_info: features: - name: text sequence: sequence: string - name: questions sequence: string - name: answers sequence: sequence: string - name: document_id dtype: string - name: split dtype: string splits: - name: train num_bytes: 26066335 num_examples: 65 download_size: 11251136 dataset_size: 26066335 configs: - config_name: default data_files: - split: train path: data/train-* ---

bellomuiz78/knowledgebase

bellomuiz78

--- license: mit ---

ashercn97/reasoning-v1-worked

ashercn97

--- dataset_info: features: - name: text_id dtype: string - name: text dtype: string - name: label sequence: string - name: split_text sequence: string splits: - name: train num_bytes: 143957 num_examples: 100 download_size: 90504 dataset_size: 143957 configs: - config_name: default data_files: - split: train path: data/train-* ---

dgambettaphd/D_gen0_run2_llama2-7b_wiki_doc1000_real32_synt96

dgambettaphd

--- dataset_info: features: - name: id dtype: int64 - name: doc dtype: string splits: - name: train num_bytes: 511648 num_examples: 1000 download_size: 301252 dataset_size: 511648 configs: - config_name: default data_files: - split: train path: data/train-* ---

julia-se/tracka_mistral_fewshot_disgust

julia-se

--- dataset_info: features: - name: id dtype: string - name: text dtype: string - name: Anger dtype: int64 - name: Disgust dtype: int64 - name: Fear dtype: int64 - name: Joy dtype: int64 - name: Sadness dtype: int64 - name: Surprise dtype: int64 - name: predicted_is_disgust dtype: int64 - name: y_disgust dtype: int64 splits: - name: train num_bytes: 472807 num_examples: 2226 download_size: 216953 dataset_size: 472807 configs: - config_name: default data_files: - split: train path: data/train-* ---

ashnaz/refined_symptoms_doctors

ashnaz

--- license: afl-3.0 ---

Taylor658/myelography-imaging

Taylor658

--- annotations_creators: - synthetic language: - en license: apache-2.0 multilinguality: - monolingual pretty_name: Myelography Imaging size_categories: - 1K<n<10K source_datasets: - original task_categories: - text-classification task_ids: - named-entity-recognition - news-articles-summarization --- # Myelography Imaging ## Dataset Description This dataset consists of **750 synthetic myelography examination records** representing a wide spectrum of spinal pathologies and patient experiences. Each record includes: - **Patient demographics**: Age and sex. - **Clinical symptoms prompting the procedure**: Detailed and verbose descriptions. - **Procedural details**: Contrast medium type, injection site, and imaging modality used. - **Verbose findings**: Observations such as spinal cord compression, herniated discs, tumors, and spinal stenosis. - **Complications encountered**: Any issues arising during or after the procedure. - **Follow-up recommendations**: Suggested next steps, including surgical consultation, physical therapy, or additional imaging. ### Example Data | Age | Sex | Clinical Symptoms | Contrast Medium Type | Injection Site | Imaging Modality | Findings | Complications | Follow-up Recommendations | |-----|-------|---------------------------------------------------------|----------------------|----------------|------------------|-------------------------------------------------|------------------------------------------|--------------------------------------------------| | 45 | Male | Chronic lower back pain with radiating leg pain | Iodinated contrast | Lumbar spine | X-ray | Large herniated disc at L4-L5 | No complications | Referral to neurosurgery for evaluation | | 60 | Female| Acute onset lower limb weakness post-trauma | Gadolinium-based contrast| Cervical spine | MRI | Severe spinal cord compression | Localized discomfort at injection site | Follow-up imaging with enhanced MRI | ## Intended Use This dataset is intended for educational, research, and development purposes, including: - Training and benchmarking in **natural language processing** (NLP) tasks. - Developing tools for medical image analysis and clinical decision support systems. - Conducting exploratory data analysis in synthetic medical datasets. ## Limitations This dataset is entirely synthetic and does not contain real patient data. It should not be used for diagnostic purposes. The findings and follow-up recommendations are simulated and may not encompass the full complexity of real-world scenarios. ## License This dataset is distributed under the **Apache 2.0 License**. ## Citation --- ### Acknowledgments

RussRobin/VDD

RussRobin

--- license: cc-by-4.0 --- VDD: Varied Drone Dataset for Semantic Segmentation Paper: https://arxiv.org/abs/2305.13608 GitHub Repo: https://github.com/RussRobin/VDD This HF repo contains VDD source images and annotations. Please refer to our GitHub Repo if you want to download our annotation of UDD and UAVid.

infinite-dataset-hub/EthicalEatingEmotions

infinite-dataset-hub

--- license: mit tags: - infinite-dataset-hub - synthetic --- # EthicalEatingEmotions tags: vegan, psychology, dietary choices _Note: This is an AI-generated dataset so its content may be inaccurate or false_ **Dataset Description:** The 'EthicalEatingEmotions' dataset contains anonymized user-generated content from various platforms discussing the emotional aspects of adopting a vegan diet. The data is gathered from social media posts, blog comments, and forum discussions. Each entry includes the original text, a sentiment analysis score, and a label reflecting the user's emotional stance towards veganism (e.g., positive, neutral, negative). **CSV Content Preview:** ``` text,sentiment_score,labels "I've been vegan for 5 years now and I feel healthier than ever!",0.9,"positive" "Trying to be vegan has been challenging but worth it for the planet.",0.7,"positive" "The taste of vegan food can sometimes be off-putting, but I'm learning.",0.6,"neutral" "I'm disappointed by the lack of vegan options at my favorite restaurant.",0.3,"negative" "Veganism isn't for everyone, and that's okay. I respect people's choices.",0.5,"neutral" ``` **Source of the data:** The dataset was generated using the [Infinite Dataset Hub](https://huggingface.co/spaces/infinite-dataset-hub/infinite-dataset-hub) and microsoft/Phi-3-mini-4k-instruct using the query 'vegan': - **Dataset Generation Page**: https://huggingface.co/spaces/infinite-dataset-hub/infinite-dataset-hub?q=vegan&dataset=EthicalEatingEmotions&tags=vegan,+psychology,+dietary+choices - **Model**: https://huggingface.co/microsoft/Phi-3-mini-4k-instruct - **More Datasets**: https://huggingface.co/datasets?other=infinite-dataset-hub

denkCF/UsersCodeforcesSubmissionsEnd2024

denkCF

--- datasets: - name: usersCodeforcesSubmissionsEnd2024 size: 200MB task_categories: - other languages: - en licenses: - cc-by-4.0 tags: - codeforces - competitive-programming - submissions pretty_name: Codeforces Users Submissions (End of 2024) description: > This dataset contains anonymized submission data of ≈15,000 Codeforces users, spanning from the inception of Codeforces to the end of November 2024. download_size: 100MB dataset_size: 1.2GB license: cc-by-4.0 language: - en tags: - codeforces - submissions size_categories: - 10M<n<100M --- # Codeforces Users Submissions Dataset (End of 2024) This project provides the usersCodeforcesSubmissionsEnd2024.csv file, containing anonymized submission data of approximately 15,000 active Codeforces users. The dataset includes all submissions from the inception of Codeforces up to the end of November 2024. It is designed to support AI and data-driven projects. (All data was collected using the open Codeforces API) ## Dataset Overview The file contains **17,607,999 rows** with the following columns: - **`handle`**: An anonymized and shuffled user nickname (e.g., `user{i}`). - **`rating_at_submission`**: User's rating at the time of submission. - **`problem_rating`**: Problem difficulty rating. - **`id_of_submission_task`**: Unique problem identifier on Codeforces. - **`verdict`**: Result of the submission (e.g., `OK`, `WRONG_ANSWER`). - **`time`**: Time of submission (in seconds since the Unix epoch). ## Purpose of the Dataset 1. **AI Development**: This dataset can be used to create intelligent systems to enhance user learning on Codeforces. _(Example: The author of this dataset is currently working on the project "Codeforces User Analysis System for Generating Individual Training Recommendations," which aims to recommend tasks to users based on their weaknesses.)_ 2. **Time Saving**: Collecting such data manually can be time-consuming (it took ≈7 hours for this dataset). By providing it in a ready-to-use format, we aim to save your time and effort. 3. **Reduce Server Load**: This dataset minimizes repetitive data scraping, thereby reducing the load on Codeforces servers. ## License This dataset is shared under the [CC BY 4.0 License](https://creativecommons.org/licenses/by/4.0/). You are free to use it for your projects with proper attribution. ## How to Use 1. Download the `usersCodeforcesSubmissionsEnd2024.zip` file. 2. Unzip the file to access the `usersCodeforcesSubmissionsEnd2024.csv` dataset: - On Linux/macOS: Use the `unzip` command in the terminal. - On Windows: Right-click the file and select "Extract All." 3. Load the CSV file into your favorite data analysis tool: ```python import pandas as pd df = pd.read_csv("usersCodeforcesSubmissionsEnd2024.csv") # Good luck with your projects :)

aniruddha007/example-retrieval-reranking-dataset

aniruddha007

--- size_categories: n<1K dataset_info: - config_name: generate_reranking_pairs features: - name: filename dtype: string - name: anchor dtype: string - name: repo_name dtype: string - name: positive dtype: string - name: negative dtype: string - name: distilabel_metadata struct: - name: raw_input_generate_reranking_pairs list: - name: content dtype: string - name: role dtype: string - name: raw_output_generate_reranking_pairs dtype: string - name: model_name dtype: string splits: - name: train num_bytes: 39508 num_examples: 15 download_size: 36985 dataset_size: 39508 - config_name: generate_retrieval_pairs features: - name: filename dtype: string - name: anchor dtype: string - name: repo_name dtype: string - name: positive dtype: string - name: negative dtype: string - name: distilabel_metadata struct: - name: raw_input_generate_retrieval_pairs list: - name: content dtype: string - name: role dtype: string - name: raw_output_generate_retrieval_pairs dtype: string - name: model_name dtype: string splits: - name: train num_bytes: 38355 num_examples: 15 download_size: 30713 dataset_size: 38355 configs: - config_name: generate_reranking_pairs data_files: - split: train path: generate_reranking_pairs/train-* - config_name: generate_retrieval_pairs data_files: - split: train path: generate_retrieval_pairs/train-* tags: - synthetic - distilabel - rlaif --- <p align="left"> <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> # Dataset Card for example-retrieval-reranking-dataset This dataset has been created with [distilabel](https://distilabel.argilla.io/). ## Dataset Summary This dataset contains a `pipeline.yaml` which can be used to reproduce the pipeline that generated it in distilabel using the `distilabel` CLI: ```console distilabel pipeline run --config "https://huggingface.co/datasets/aniruddha007/example-retrieval-reranking-dataset/raw/main/pipeline.yaml" ``` or explore the configuration: ```console distilabel pipeline info --config "https://huggingface.co/datasets/aniruddha007/example-retrieval-reranking-dataset/raw/main/pipeline.yaml" ``` ## Dataset structure The examples have the following structure per configuration: <details><summary> Configuration: generate_retrieval_pairs </summary><hr> ```json { "anchor": "description: Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.\nhide: navigation\n\nWelcome to Argilla\n\nArgilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.", "distilabel_metadata": { "raw_input_generate_retrieval_pairs": [ { "content": "Your task is to generate a positive and a negative sentence given an anchor sentence. Take into account the context given. The positive sentence has to be a query for the anchor sentence, while the negative sentence is a \u0027hard negative\u0027 that meets the following criteria:\n- Uses similar keywords or phrases as the anchor sentence\n- Has a similar grammatical structure or syntax\n- Is not related to the anchor sentence, but could be mistaken for it\nTry to create a negative sentence that would be challenging for a model to distinguish from the positive sentence. You must output only two new sections: `## Positive` and `## Negative`.", "role": "system" }, { "content": "## Context\n\n\nThe text is a chunk from technical Python SDK documentation of Argilla.\nArgilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets.\nAlong with prose explanations, the text chunk may include code snippets and Python references.\n\n\n## Anchor\n\ndescription: Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.\nhide: navigation\n\nWelcome to Argilla\n\nArgilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.\n", "role": "user" } ], "raw_output_generate_retrieval_pairs": "## Positive\nWhat is Argilla, the collaboration tool for AI engineers and domain experts, that offers high-quality outputs, full data ownership, and overall efficiency?\n\n## Negative\nArgilla is a collaboration platform for AI engineers and domain experts that demand low-quality outputs, limited data ownership, and overall inefficiency." }, "filename": "argilla-python/docs/index.md", "model_name": "mistralai/Mistral-7B-Instruct-v0.3", "negative": "Argilla is a collaboration platform for AI engineers and domain experts that demand low-quality outputs, limited data ownership, and overall inefficiency.", "positive": "What is Argilla, the collaboration tool for AI engineers and domain experts, that offers high-quality outputs, full data ownership, and overall efficiency?", "repo_name": "argilla-io/argilla-python" } ``` This subset can be loaded as: ```python from datasets import load_dataset ds = load_dataset("aniruddha007/example-retrieval-reranking-dataset", "generate_retrieval_pairs") ``` </details> <details><summary> Configuration: generate_reranking_pairs </summary><hr> ```json { "anchor": "description: Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.\nhide: navigation\n\nWelcome to Argilla\n\nArgilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.", "distilabel_metadata": { "raw_input_generate_reranking_pairs": [ { "content": "Your task is to generate a positive and a negative sentence given an anchor sentence. Take into account the context given. The positive sentence has to be semantically similar to the anchor sentence, while the negative sentence can use similar words but must not be related to the anchor sentence. You must output only two new sections: `## Positive` and `## Negative`.", "role": "system" }, { "content": "## Context\n\n\nThe text is a chunk from technical Python SDK documentation of Argilla.\nArgilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets.\nAlong with prose explanations, the text chunk may include code snippets and Python references.\n\n\n## Anchor\n\ndescription: Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.\nhide: navigation\n\nWelcome to Argilla\n\nArgilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.\n", "role": "user" } ], "raw_output_generate_reranking_pairs": "## Positive\nArgilla offers an efficient and collaborative environment for AI engineers and domain experts to produce superior quality datasets while maintaining full control over their data.\n\n## Negative\nUnfortunately, Argilla does not support real-time data streaming or AI model training, making it less suitable for certain fast-paced AI project requirements." }, "filename": "argilla-python/docs/index.md", "model_name": "mistralai/Mistral-7B-Instruct-v0.3", "negative": "Unfortunately, Argilla does not support real-time data streaming or AI model training, making it less suitable for certain fast-paced AI project requirements.", "positive": "Argilla offers an efficient and collaborative environment for AI engineers and domain experts to produce superior quality datasets while maintaining full control over their data.", "repo_name": "argilla-io/argilla-python" } ``` This subset can be loaded as: ```python from datasets import load_dataset ds = load_dataset("aniruddha007/example-retrieval-reranking-dataset", "generate_reranking_pairs") ``` </details>

yspark0519/iemocap_add_features

yspark0519

--- dataset_info: features: - name: messages list: - name: content list: - name: text dtype: string - name: type dtype: string - name: role dtype: string - name: images sequence: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 1880275 num_examples: 3548 - name: test num_bytes: 493491 num_examples: 942 download_size: 551240 dataset_size: 2373766 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

babs/podcast-9

babs

--- dataset_info: features: - name: audio dtype: audio - name: transcription dtype: string splits: - name: train num_bytes: 193557411.0 num_examples: 275 download_size: 181264413 dataset_size: 193557411.0 configs: - config_name: default data_files: - split: train path: data/train-* ---

viktoriatilevska/train_group3_1M

viktoriatilevska

--- dataset_info: features: - name: context dtype: string - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 384600002 num_examples: 1000000 download_size: 76733429 dataset_size: 384600002 configs: - config_name: default data_files: - split: train path: data/train-* ---

Alwaly/parler_tts_wom

Alwaly

--- dataset_info: features: - name: text dtype: string - name: utterance_pitch_mean dtype: float32 - name: utterance_pitch_std dtype: float32 - name: snr dtype: float64 - name: c50 dtype: float64 - name: speaking_rate dtype: float64 - name: phonemes dtype: string - name: stoi dtype: float64 - name: si-sdr dtype: float64 - name: pesq dtype: float64 splits: - name: train num_bytes: 1925479 num_examples: 17952 - name: test num_bytes: 215369 num_examples: 1995 download_size: 1812661 dataset_size: 2140848 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

juliadollis/stf_regex_ner_2_fuzzyover_90

juliadollis

--- dataset_info: features: - name: inteiro_teor dtype: string - name: url_download dtype: string - name: dataDecisao dtype: timestamp[ns] - name: dataPublicacao dtype: timestamp[ns] - name: decisao dtype: string - name: descricaoClasse dtype: string - name: ementa dtype: string - name: id dtype: string - name: jurisprudenciaCitada dtype: string - name: ministroRelator dtype: string - name: nomeOrgaoJulgador dtype: string - name: numeroProcesso dtype: string - name: referenciasLegislativas sequence: string - name: siglaClasse dtype: string - name: tipoDeDecisao dtype: string - name: titulo dtype: string - name: acordaosSimilares sequence: string - name: partes_lista_texto dtype: string - name: temaProcs sequence: string - name: inteiro_teor_regex dtype: string - name: NER struct: - name: JURISPRUDENCIA sequence: string - name: LEGISLACAO sequence: string - name: LOCAL sequence: string - name: ORGANIZACAO sequence: string - name: PESSOA sequence: string - name: TEMPO sequence: string - name: desambiguacao list: - name: class dtype: string - name: count dtype: int64 - name: elements sequence: string - name: entity dtype: string splits: - name: train num_bytes: 159167208 num_examples: 1000 download_size: 44085104 dataset_size: 159167208 configs: - config_name: default data_files: - split: train path: data/train-* ---

mlfoundations-dev/opengpt_gpt-4o-mini_scale_x.125

mlfoundations-dev

--- dataset_info: features: - name: language dtype: string - name: quantity dtype: int64 - name: task dtype: string - name: instruction dtype: string - name: input dtype: string - name: output dtype: string - name: conversations list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 1749694 num_examples: 498 download_size: 854812 dataset_size: 1749694 configs: - config_name: default data_files: - split: train path: data/train-* ---

mlfoundations-dev/opengpt_gpt-4o-mini_scale_x.5

mlfoundations-dev

--- dataset_info: features: - name: language dtype: string - name: quantity dtype: int64 - name: task dtype: string - name: instruction dtype: string - name: input dtype: string - name: output dtype: string - name: conversations list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 5171805 num_examples: 2466 download_size: 2656285 dataset_size: 5171805 configs: - config_name: default data_files: - split: train path: data/train-* ---

DT4LM/t5v1-1base_sst2_leap

DT4LM

--- dataset_info: features: - name: text dtype: string - name: label dtype: int32 splits: - name: train num_bytes: 48903 num_examples: 662 download_size: 34435 dataset_size: 48903 configs: - config_name: default data_files: - split: train path: data/train-* ---

all-oj-gen/ds_coder_reflct_rmsprop_iter4_sppo_hard_new_all_oj_iter4-bin_all_pairs

all-oj-gen

--- dataset_info: features: - name: prompt dtype: string - name: chosen dtype: string - name: rejected dtype: string - name: rejected_traceback dtype: string - name: test dtype: string splits: - name: train num_bytes: 37426071 num_examples: 9188 download_size: 11275871 dataset_size: 37426071 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "ds_coder_reflct_rmsprop_iter4_sppo_hard_new_all_oj_iter4-bin_all_pairs" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

aboriskin/adaptive_rag_hotpotqa

aboriskin

--- license: apache-2.0 task_categories: - question-answering language: - en size_categories: - n<1K --- In this collection you can find 4 datasets with `is_supporting=True` contexts from the Adaptive RAG collection. There are picked 4/6 datasets from Adaptive RAG datasets with `is_supporting=True` contexts. Not all samples from TriviaQA and SQUAD have `is_supporting=True` contexts, thats why we do not include them in hf collection. If question have more than one `is_supporting=True` context, we concatenate them. Script for data transformation from original Adaptive RAG format into our format can be found here: https://github.com/sashaboriskin/rag_routing/blob/main/data/hf_adaptive_rag_supportive_context.py

all-oj-gen/ds_chat_pos_reflct_rmsprop_iter1_sppo_hard_new_all_oj_iter1-bin

all-oj-gen

--- dataset_info: features: - name: prompt dtype: string - name: chosen dtype: string - name: rejected dtype: string - name: rejected_traceback dtype: string - name: chosen_probs dtype: float64 - name: chosen_probs_win dtype: float64 - name: chosen_probs_lose dtype: float64 splits: - name: train num_bytes: 17187060 num_examples: 5909 download_size: 7065544 dataset_size: 17187060 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "ds_chat_pos_reflct_rmsprop_iter1_sppo_hard_new_all_oj_iter1-bin" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

RyanYr/self-reflect_mini8Bit-t0_mistlarge-t12_om2-460k_binlabel_reflection

RyanYr

--- dataset_info: features: - name: prompt dtype: string - name: response dtype: string - name: response@0_correctness dtype: bool - name: response@2_correctness dtype: bool splits: - name: train num_bytes: 712727727 num_examples: 247730 download_size: 261524199 dataset_size: 712727727 configs: - config_name: default data_files: - split: train path: data/train-* ---

Alwaly/parler_tts-descriptions-tags_bis_wom

Alwaly

--- dataset_info: features: - name: text dtype: string - name: utterance_pitch_mean dtype: float32 - name: utterance_pitch_std dtype: float32 - name: snr dtype: float64 - name: c50 dtype: float64 - name: speaking_rate dtype: string - name: phonemes dtype: string - name: stoi dtype: float64 - name: si-sdr dtype: float64 - name: pesq dtype: float64 - name: noise dtype: string - name: reverberation dtype: string - name: speech_monotony dtype: string - name: sdr_noise dtype: string - name: pesq_speech_quality dtype: string - name: text_description dtype: string splits: - name: train num_bytes: 7000548 num_examples: 17952 - name: test num_bytes: 784386 num_examples: 1995 download_size: 3004619 dataset_size: 7784934 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

asoria/crawl4ai_hf_page_md

asoria

--- tags: - crawl4ai - crawl --- **Source of the data:** The dataset was generated using [Crawl4ai](https://crawl4ai.com/mkdocs/) library from https://huggingface.co/.

mlgawd/final_dpo_nemo_v9

mlgawd

--- dataset_info: features: - name: questions dtype: string - name: accepted dtype: string - name: rejected dtype: string splits: - name: train num_bytes: 28102869 num_examples: 5877 download_size: 15924726 dataset_size: 28102869 configs: - config_name: default data_files: - split: train path: data/train-* ---

collinear-ai/financial_cg_flex_customization

collinear-ai

--- dataset_info: features: - name: conv_prefix list: - name: content dtype: string - name: role dtype: string - name: response struct: - name: content dtype: string - name: role dtype: string - name: ground_truth dtype: int64 splits: - name: pku_safer_rlhf_economic_crime num_bytes: 1267 num_examples: 2 download_size: 7552 dataset_size: 1267 configs: - config_name: default data_files: - split: pku_safer_rlhf_economic_crime path: data/pku_safer_rlhf_economic_crime-* ---

Honi086/voz_natanzinholima

Honi086

--- license: openrail ---

mlgawd/final_dpo_nemo_v15

mlgawd

--- dataset_info: features: - name: questions dtype: string - name: accepted dtype: string - name: rejected dtype: string splits: - name: train num_bytes: 28050268.76875957 num_examples: 5866 download_size: 15945218 dataset_size: 28050268.76875957 configs: - config_name: default data_files: - split: train path: data/train-* ---

BarryFutureman/jenny-tts-text-tags-6h-v1

BarryFutureman

--- dataset_info: features: - name: file_name dtype: string - name: text dtype: string - name: transcription_normalised dtype: string - name: utterance_pitch_mean dtype: float32 - name: utterance_pitch_std dtype: float32 - name: snr dtype: float64 - name: c50 dtype: float64 - name: speaking_rate dtype: string - name: phonemes dtype: string - name: stoi dtype: float64 - name: si-sdr dtype: float64 - name: pesq dtype: float64 - name: noise dtype: string - name: reverberation dtype: string - name: speech_monotony dtype: string - name: sdr_noise dtype: string - name: pesq_speech_quality dtype: string splits: - name: train num_bytes: 2063542 num_examples: 4000 download_size: 1025292 dataset_size: 2063542 configs: - config_name: default data_files: - split: train path: data/train-* ---

HFXM/hh-rlhf-Rule7

HFXM

--- dataset_info: features: - name: chosen dtype: string - name: rejected dtype: string splits: - name: train num_bytes: 325133436 num_examples: 169352 download_size: 183445975 dataset_size: 325133436 configs: - config_name: default data_files: - split: train path: data/train-* ---

CambioMoney/ami-speaker-analysis_full_run_3

CambioMoney

--- dataset_info: features: - name: meeting_id dtype: string - name: audio_id dtype: string - name: text dtype: string - name: audio struct: - name: array sequence: float64 - name: path dtype: string - name: sampling_rate dtype: int64 - name: begin_time dtype: float64 - name: end_time dtype: float64 - name: microphone_id dtype: string - name: speaker_id dtype: string - name: is_complete dtype: bool - name: original_segment dtype: bool splits: - name: train num_bytes: 204976583 num_examples: 459 - name: validation num_bytes: 165869849 num_examples: 434 - name: test num_bytes: 112767531 num_examples: 418 download_size: 102500074 dataset_size: 483613963 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* ---

mathreward/new_8b_llama31_selfcorr_horizon2_tmp07

mathreward

--- dataset_info: features: - name: idx dtype: int64 - name: gt dtype: string - name: level dtype: string - name: type dtype: string - name: my_solu dtype: string - name: pred sequence: string splits: - name: train num_bytes: 22370291 num_examples: 5000 download_size: 6772341 dataset_size: 22370291 --- # Dataset Card for "new_8b_llama31_selfcorr_horizon2_tmp07" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

polymathic-ai/turbulent_radiative_layer_2D

polymathic-ai

--- language: - en license: cc-by-4.0 tags: - physics task_categories: - time-series-forecasting - other task_ids: - multivariate-time-series-forecasting --- # How To Load from HuggingFace Hub 1. Be sure to have `the_well` installed (`pip install the_well`) 2. Use the `WellDataModule` to retrieve data as follows: ```python from the_well.data import WellDataModule # The following line may take a couple of minutes to instantiate the datamodule datamodule = WellDataModule( "hf://datasets/polymathic-ai/", "turbulent_radiative_layer_2D", ) train_dataloader = datamodule.train_dataloader() for batch in dataloader: # Process training batch ... ``` # Turbulent Radiative Layer - 2D **One line description of the data:** Everywhere in astrophysical systems hot gas moves relative to cold gas, which leads to mixing, and mixing populates intermediate temperature gas that is highly reactive—in this case it is rapidly cooling. **Longer description of the data:** In this simulation, there is cold, dense gas on the bottom and hot dilute gas on the top. They are moving relative to each other at highly subsonic velocities. This set up is unstable to the Kelvin Helmholtz instability, which is seeded with small scale noise that is varied between the simulations. The hot gas and cold gas are both in thermal equilibrium in the sense that the heating and cooling are exactly balanced. However, once mixing occurs as a result of the turbulence induced by the Kelvin Helmholtz instability the intermediate temperatures become populated. This intermediate temperature gas is not in thermal equilibrium and cooling beats heating. This leads to a net mass flux from the hot phase to the cold phase. This process occurs in the interstellar medium, and in the Circum-Galactic medium when cold clouds move through the ambient, hot medium. By understanding how the total cooling and mass transfer scale with the cooling rate we are able to constrain how this process controls the overall phase structure, energetics and dynamics of the gas in and around galaxies. **Associated paper**: [Paper](https://iopscience.iop.org/article/10.3847/2041-8213/ab8d2c/pdf). **Domain expert**: [Drummond Fielding](https://dfielding14.github.io/), CCA, Flatiron Institute & Cornell University. **Code or software used to generate the data**: [Athena++](https://www.athena-astro.app/). **Equation**: $$ \begin{align*} \frac{ \partial \rho}{\partial t} + \nabla \cdot \left( \rho \vec{v} \right) &= 0 \\ \frac{ \partial \rho \vec{v} }{\partial t} + \nabla \cdot \left( \rho \vec{v}\vec{v} + P \right) &= 0 \\ \frac{ \partial E }{\partial t} + \nabla \cdot \left( (E + P) \vec{v} \right) &= - \frac{E}{t_{\rm cool}} \\ E = P / (\gamma -1) \, \, \gamma &= 5/3 \end{align*} $$ with \\(\rho\\) the density, \\(\vec{v}\\) the 2D velocity, \\(P\\) the pressure, \\(E\\) the total energy, and \\(t_{\rm cool}\\) the cooling time.  | Dataset | FNO | TFNO | Unet | CNextU-net |:-:|:-:|:-:|:-:|:-:| | `turbulent_radiative_layer_2D` | 0.5001| 0.5016 |0.2418| \\(\mathbf{0.1956}\\)| Table: VRMSE metrics on test sets (lower is better). Best results are shown in bold. VRMSE is scaled such that predicting the mean value of the target field results in a score of 1. ## About the data **Dimension of discretized data:** 101 timesteps of 384x128 images. **Fields available in the data:** Density (scalar field), pressure (scalar field), velocity (vector field). **Number of trajectories:** 90 (10 different seeds for each of the 9 \\(t_{cool}\\) values). **Estimated size of the ensemble of all simulations:** 6.9 GB. **Grid type:** uniform, cartesian coordinates. **Initial conditions:** Analytic, described in the [paper](https://ui.adsabs.harvard.edu/abs/2020ApJ...894L..24F/abstract). **Boundary conditions:** Periodic in the x-direction, zero-gradient for the y-direction. **Simulation time-step ( \\(\Delta t\\)):** varies with \\(t_{cool}\\). Smallest \\(t_{cool}\\) has \\(\Delta t = 1.36\times10^{-2}\\) and largest \\(t_{cool}\\) has \\(\Delta t = 1.74\times10^{-2}\\). Not that this is not in seconds. This is in dimensionless simulation time. **Data are stored separated by ( \\(\delta t\\)):** 1.597033 in simulation time. **Total time range ( \\(t_{min}\\) to \\(t_{max}\\)):** \\(t_{min} = 0\\), \\(t_{max} = 159.7033\\). **Spatial domain size ( \\(L_x\\), \\(L_y\\), \\(L_z\\)):** \\(x \in [-0.5, 0.5]\\), \\(y \in [-1, 2]\\) giving \\(L_x = 1\\) and \\(L_y = 3\\). **Set of coefficients or non-dimensional parameters evaluated:** \\(t_{cool} = \{0.03, 0.06, 0.1, 0.18, 0.32, 0.56, 1.00, 1.78, 3.16\}\\). **Approximate time to generate the data:** 84 seconds using 48 cores for one simulation. 100 CPU hours for everything. **Hardware used to generate the data:** 48 CPU cores. ## What is interesting and challenging about the data: **What phenomena of physical interest are catpured in the data:** - The mass flux from hot to cold phase. - The turbulent velocities. - Amount of mass per temperature bin (T = press/dens). **How to evaluate a new simulator operating in this space:** See whether it captures the right mass flux, the right turbulent velocities, and the right amount of mass per temperature bin. Please cite the associated paper if you use this data in your research: ``` @article{fielding2020multiphase, title={Multiphase gas and the fractal nature of radiative turbulent mixing layers}, author={Fielding, Drummond B and Ostriker, Eve C and Bryan, Greg L and Jermyn, Adam S}, journal={The Astrophysical Journal Letters}, volume={894}, number={2}, pages={L24}, year={2020}, publisher={IOP Publishing} } ```

CambioMoney/ami-speaker-analysis_full_run_deepgram_4_train

CambioMoney

--- dataset_info: features: - name: meeting_id dtype: string - name: audio_id dtype: string - name: text dtype: string - name: audio struct: - name: array sequence: float64 - name: path dtype: string - name: sampling_rate dtype: int64 - name: begin_time dtype: float64 - name: end_time dtype: float64 - name: microphone_id dtype: string - name: speaker_id dtype: string - name: is_complete dtype: bool - name: original_segment dtype: bool - name: confidence dtype: float64 splits: - name: train num_bytes: 64287453 num_examples: 100 download_size: 12880587 dataset_size: 64287453 configs: - config_name: default data_files: - split: train path: data/train-* ---

RyanYr/self-reflect_mini8Bit-t0_sft-t1_om2-1

RyanYr

--- dataset_info: features: - name: problem dtype: string - name: generated_solution dtype: string - name: answer dtype: string - name: problem_source dtype: string - name: response@0 sequence: string - name: response@1 sequence: string splits: - name: train num_bytes: 200430782 num_examples: 20000 download_size: 74218427 dataset_size: 200430782 configs: - config_name: default data_files: - split: train path: data/train-* ---

ziyu3141/rich_feedback_train_with_image

ziyu3141

--- dataset_info: features: - name: Filename dtype: string - name: Aesthetics score dtype: float64 - name: Artifact score dtype: float64 - name: Misalignment score dtype: float64 - name: Overall score dtype: float64 - name: Artifact heatmap sequence: sequence: sequence: int64 - name: Misalignment heatmap sequence: sequence: sequence: int64 - name: Misalignment token label dtype: string - name: prompt dtype: string - name: image dtype: binary splits: - name: train num_bytes: 101068478704 num_examples: 15810 download_size: 1715550658 dataset_size: 101068478704 configs: - config_name: default data_files: - split: train path: data/train-* ---

all-oj-gen/ds_coder_pos_reflct_rmsprop_iter1_sppo_hard_new_all_oj_iter1-bin

all-oj-gen

--- dataset_info: features: - name: prompt dtype: string - name: chosen dtype: string - name: rejected dtype: string - name: rejected_traceback dtype: string - name: chosen_probs dtype: float64 - name: chosen_probs_win dtype: float64 - name: chosen_probs_lose dtype: float64 splits: - name: train num_bytes: 22694827 num_examples: 5803 download_size: 9769195 dataset_size: 22694827 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "ds_coder_pos_reflct_rmsprop_iter1_sppo_hard_new_all_oj_iter1-bin" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

all-oj-gen/ds_coder_pos_reflct_rmsprop_iter1_sppo_hard_new_all_oj_iter1-full_resp_trace

all-oj-gen

--- dataset_info: features: - name: prompt dtype: string - name: test dtype: string - name: tag dtype: string - name: id dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: text_prompt dtype: string - name: text_chosen dtype: string - name: text_rejected dtype: string - name: generate_0 dtype: string - name: generate_0_score dtype: int64 - name: traceback_0 dtype: string - name: generate_1 dtype: string - name: generate_1_score dtype: int64 - name: traceback_1 dtype: string - name: generate_2 dtype: string - name: generate_2_score dtype: int64 - name: traceback_2 dtype: string - name: generate_3 dtype: string - name: generate_3_score dtype: int64 - name: traceback_3 dtype: string - name: probability sequence: sequence: float64 - name: rm_scores sequence: int64 splits: - name: train num_bytes: 58672389 num_examples: 5803 download_size: 22470758 dataset_size: 58672389 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "ds_coder_pos_reflct_rmsprop_iter1_sppo_hard_new_all_oj_iter1-full_resp_trace" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

Senju2/Context-Aware-English-to-Arabic-Dataset

Senju2

--- license: artistic-2.0 language: - ar - en ---

ShravaniCV/guanaco-llama2-1k

ShravaniCV

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 1654448 num_examples: 1000 download_size: 966692 dataset_size: 1654448 configs: - config_name: default data_files: - split: train path: data/train-* ---

all-oj-gen/ds_coder_pos_reflct_rmsprop_iter2_sppo_hard_new_all_oj_iter2-bin

all-oj-gen

--- dataset_info: features: - name: prompt dtype: string - name: chosen dtype: string - name: rejected dtype: string - name: rejected_traceback dtype: string - name: chosen_probs dtype: float64 - name: chosen_probs_win dtype: float64 - name: chosen_probs_lose dtype: float64 splits: - name: train num_bytes: 20501335 num_examples: 5330 download_size: 8790051 dataset_size: 20501335 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "ds_coder_pos_reflct_rmsprop_iter2_sppo_hard_new_all_oj_iter2-bin" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

all-oj-gen/ds_coder_pos_reflct_rmsprop_iter2_sppo_hard_new_all_oj_iter2-full_resp_trace

all-oj-gen

--- dataset_info: features: - name: prompt dtype: string - name: test dtype: string - name: tag dtype: string - name: id dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: text_prompt dtype: string - name: text_chosen dtype: string - name: text_rejected dtype: string - name: generate_0 dtype: string - name: generate_0_score dtype: int64 - name: traceback_0 dtype: string - name: generate_1 dtype: string - name: generate_1_score dtype: int64 - name: traceback_1 dtype: string - name: generate_2 dtype: string - name: generate_2_score dtype: int64 - name: traceback_2 dtype: string - name: generate_3 dtype: string - name: generate_3_score dtype: int64 - name: traceback_3 dtype: string - name: probability sequence: sequence: float64 - name: rm_scores sequence: int64 splits: - name: train num_bytes: 53264044 num_examples: 5330 download_size: 20304959 dataset_size: 53264044 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "ds_coder_pos_reflct_rmsprop_iter2_sppo_hard_new_all_oj_iter2-full_resp_trace" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

likithguna/guanaco-llama2-1k

likithguna

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 1654448 num_examples: 1000 download_size: 966692 dataset_size: 1654448 configs: - config_name: default data_files: - split: train path: data/train-* ---

gswamy/pythia-1.4B-tldr-vllm-pair-iter-3

gswamy

--- dataset_info: features: - name: info struct: - name: id dtype: string - name: post dtype: string - name: title dtype: string - name: subreddit dtype: string - name: site dtype: string - name: article dtype: string - name: summaries list: - name: text dtype: string - name: policy dtype: string - name: note dtype: string - name: choice dtype: int32 - name: worker dtype: string - name: batch dtype: string - name: split dtype: string - name: extra struct: - name: confidence dtype: int32 - name: query_token sequence: int64 - name: query dtype: string - name: response0 dtype: string - name: response0_token sequence: int64 - name: response0_token_len dtype: int64 - name: response0_policy dtype: string - name: query_response0 dtype: string - name: query_response0_token sequence: int64 - name: query_response0_token_len dtype: int64 - name: query_response0_token_response_label sequence: int64 - name: response1 dtype: string - name: response1_token sequence: int64 - name: response1_token_len dtype: int64 - name: response1_policy dtype: string - name: query_response1 dtype: string - name: query_response1_token sequence: int64 - name: query_response1_token_len dtype: int64 - name: query_response1_token_response_label sequence: int64 - name: query_token_len dtype: int64 - name: policies dtype: string - name: iter_3_best_query_response sequence: int64 - name: iter_3_worst_query_response sequence: int64 - name: iter_3_best_mask sequence: int64 - name: iter_3_worst_mask sequence: int64 - name: iter_3_best_reward dtype: float64 - name: iter_3_worst_reward dtype: float64 splits: - name: train num_bytes: 4841788931 num_examples: 92858 download_size: 186299631 dataset_size: 4841788931 configs: - config_name: default data_files: - split: train path: data/train-* ---

utkarsh4430/pretraining

utkarsh4430

--- dataset_info: features: - name: id dtype: string - name: instruction dtype: string - name: output dtype: string - name: dataset dtype: string - name: task dtype: string - name: input dtype: string - name: audio_feat dtype: binary - name: video_feat dtype: binary splits: - name: train num_bytes: 38631914922 num_examples: 485830 download_size: 36262540214 dataset_size: 38631914922 configs: - config_name: default data_files: - split: train path: data/train-* ---

Nachiket-S/LLaMa_1B_NoCoT_DebiasingInstruction

Nachiket-S

--- dataset_info: features: - name: file_name dtype: string - name: paragraph dtype: string - name: generated_text dtype: string splits: - name: inference num_bytes: 125517 num_examples: 80 download_size: 48320 dataset_size: 125517 configs: - config_name: default data_files: - split: inference path: data/inference-* ---

tdurbor/background-removal-arena-green

tdurbor

--- dataset_info: features: - name: original_image dtype: image - name: clipdrop_image dtype: image - name: bria_image dtype: image - name: photoroom_image dtype: image - name: removebg_image dtype: image - name: original_filename dtype: string splits: - name: train num_bytes: 147718672.0 num_examples: 77 download_size: 147674887 dataset_size: 147718672.0 configs: - config_name: default data_files: - split: train path: data/train-* ---

jfcalvo/export-testing-different-split

jfcalvo

--- tags: - rlfh - argilla - human-feedback --- # Dataset Card for export-testing-different-split This dataset has been created with [Argilla](https://github.com/argilla-io/argilla). As shown in the sections below, this dataset can be loaded into your Argilla server as explained in [Load with Argilla](#load-with-argilla), or used directly with the `datasets` library in [Load with `datasets`](#load-with-datasets). ## Using this dataset with Argilla To load with Argilla, you'll just need to install Argilla as `pip install argilla --upgrade` and then use the following code: ```python import argilla as rg ds = rg.Dataset.from_hub("jfcalvo/export-testing-different-split", settings="auto") ``` This will load the settings and records from the dataset repository and push them to you Argilla server for exploration and annotation. ## Using this dataset with `datasets` To load the records of this dataset with `datasets`, you'll just need to install `datasets` as `pip install datasets --upgrade` and then use the following code: ```python from datasets import load_dataset ds = load_dataset("jfcalvo/export-testing-different-split") ``` This will only load the records of the dataset, but not the Argilla settings. ## Dataset Structure This dataset repo contains: * Dataset records in a format compatible with HuggingFace `datasets`. These records will be loaded automatically when using `rg.Dataset.from_hub` and can be loaded independently using the `datasets` library via `load_dataset`. * The [annotation guidelines](#annotation-guidelines) that have been used for building and curating the dataset, if they've been defined in Argilla. * A dataset configuration folder conforming to the Argilla dataset format in `.argilla`. The dataset is created in Argilla with: **fields**, **questions**, **suggestions**, **metadata**, **vectors**, and **guidelines**. ### Fields The **fields** are the features or text of a dataset's records. For example, the 'text' column of a text classification dataset of the 'prompt' column of an instruction following dataset. | Field Name | Title | Type | Required | | ---------- | ----- | ---- | -------- | | persona | persona | text | False | | image | image | image | False | ### Questions The **questions** are the questions that will be asked to the annotators. They can be of different types, such as rating, text, label_selection, multi_label_selection, or ranking. | Question Name | Title | Type | Required | Description | Values/Labels | | ------------- | ----- | ---- | -------- | ----------- | ------------- | | text_0 | text_0 | text | True | N/A | N/A | | label_1 | label_1 | label_selection | True | N/A | [] | | multi-label_2 | multi-label_2 | multi_label_selection | True | N/A | [] | | rating_3 | rating_3 | rating | True | N/A | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10] | | ranking_4 | ranking_4 | ranking | True | N/A | ['option1', 'option2'] | | span_5 | span_5 | span | True | N/A | N/A | <!-- check length of metadata properties --> ### Data Splits The dataset contains a single split, which is `train`. ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation guidelines [More Information Needed] #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citation Information [More Information Needed] ### Contributions [More Information Needed]

VargheseP/test_dataset_area_asc

VargheseP

--- dataset_info: features: - name: image dtype: image - name: bbx dtype: image - name: dist dtype: image - name: ellipse dtype: image - name: basic dtype: string - name: artsy dtype: string - name: caption dtype: string - name: mask dtype: image splits: - name: train num_bytes: 84262821.0 num_examples: 931 download_size: 81324540 dataset_size: 84262821.0 configs: - config_name: default data_files: - split: train path: data/train-* ---

cuijinye/so106_test

cuijinye

--- license: apache-2.0 task_categories: - robotics tags: - LeRobot - so100 - tutorial configs: - config_name: default data_files: data/*/*.parquet --- This dataset was created using [LeRobot](https://github.com/huggingface/lerobot). ## Dataset Description - **Homepage:** [More Information Needed] - **Paper:** [More Information Needed] - **License:** apache-2.0 ## Dataset Structure [meta/info.json](meta/info.json): ```json { "codebase_version": "v2.0", "robot_type": "so100", "total_episodes": 2, "total_frames": 1016, "total_tasks": 1, "total_videos": 4, "total_chunks": 1, "chunks_size": 1000, "fps": 30, "splits": { "train": "0:2" }, "data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet", "video_path": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4", "features": { "action": { "dtype": "float32", "shape": [ 6 ], "names": [ "main_shoulder_pan", "main_shoulder_lift", "main_elbow_flex", "main_wrist_flex", "main_wrist_roll", "main_gripper" ] }, "observation.state": { "dtype": "float32", "shape": [ 6 ], "names": [ "main_shoulder_pan", "main_shoulder_lift", "main_elbow_flex", "main_wrist_flex", "main_wrist_roll", "main_gripper" ] }, "observation.images.laptop": { "dtype": "video", "shape": [ 480, 640, 3 ], "names": [ "height", "width", "channels" ], "info": { "video.fps": 30.0, "video.height": 480, "video.width": 640, "video.channels": 3, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "observation.images.phone": { "dtype": "video", "shape": [ 480, 640, 3 ], "names": [ "height", "width", "channels" ], "info": { "video.fps": 30.0, "video.height": 480, "video.width": 640, "video.channels": 3, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "timestamp": { "dtype": "float32", "shape": [ 1 ], "names": null }, "frame_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "episode_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "task_index": { "dtype": "int64", "shape": [ 1 ], "names": null } } } ``` ## Citation **BibTeX:** ```bibtex [More Information Needed] ```

all-oj-gen/ds_coder6.7b_pos_reflct_rmsprop_iter2_sppo_hard_new_all_oj_iter2-bin

all-oj-gen

--- dataset_info: features: - name: prompt dtype: string - name: chosen dtype: string - name: rejected dtype: string - name: rejected_traceback dtype: string - name: chosen_probs dtype: float64 - name: chosen_probs_win dtype: float64 - name: chosen_probs_lose dtype: float64 splits: - name: train num_bytes: 18544306 num_examples: 5387 download_size: 8159425 dataset_size: 18544306 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "ds_coder6.7b_pos_reflct_rmsprop_iter2_sppo_hard_new_all_oj_iter2-bin" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

Sebastianycx/alpaca_train_cleaned

Sebastianycx

--- license: mit ---

AsmaaMahmoudSaeddd/testdataset7

AsmaaMahmoudSaeddd

--- dataset_info: features: - name: image dtype: image - name: label dtype: string splits: - name: train num_bytes: 91277.0 num_examples: 3 download_size: 91579 dataset_size: 91277.0 configs: - config_name: default data_files: - split: train path: data/train-* ---

RyanYr/self-reflect_mini8Bit-t0_sft-t1_om2-1_2

RyanYr

--- dataset_info: features: - name: problem dtype: string - name: generated_solution dtype: string - name: answer dtype: string - name: problem_source dtype: string - name: response@0 sequence: string - name: response@1 sequence: string splits: - name: train num_bytes: 819468626 num_examples: 80000 download_size: 303055898 dataset_size: 819468626 configs: - config_name: default data_files: - split: train path: data/train-* ---

marco-schouten/exp11

marco-schouten

--- dataset_info: features: - name: input_image dtype: image - name: edit_prompt dtype: string - name: edited_image dtype: image splits: - name: train num_bytes: 1313588.0 num_examples: 311 download_size: 513217 dataset_size: 1313588.0 configs: - config_name: default data_files: - split: train path: data/train-* ---

Geraldine/Ead-Instruct-full-175k

Geraldine

--- dataset_info: features: - name: prompt dtype: string - name: completion dtype: string splits: - name: train num_bytes: 62975299 num_examples: 175410 download_size: 8413170 dataset_size: 62975299 configs: - config_name: default data_files: - split: train path: data/train-* --- # EAD/XML Dataset for Prompt-Completion Tasks ## Overview This dataset is specifically designed for text generation and completion tasks involving Encoded Archival Description (EAD) files in XML format. The dataset provides four distinct types of prompt-completion pairs, each crafted to help train and evaluate language models in understanding hierarchical XML structures, element relationships, path-based predictions, and masked element generation. ## Dataset summary This dataset is designed for fine-tuning large language models to generate and complete XML files compliant with the EAD (Encoded Archival Description) standard. It emphasizes structural and semantic understanding of deeply nested XML elements, commonly used for archival metadata representation. The dataset consists of: - XML snippets and sections extracted from real-world EAD/XML files. - Examples designed to balance structural integrity, attribute handling, and meaningful textual content. - Diverse prompts, including partial, truncated, and complete XML sections. ## Dataset creation ### Source Data The source XML files were derived from the French `Inventaires du Catalogue général des manuscrits (CGM)` of the BnF collections. These files adhere to the EAD schema and were processed programmatically to create structured training examples. ### Processing Pipeline The dataset was generated using a Python pipeline leveraging the lxml and xml.etree.ElementTree libraries. Example ``` def hierarchical_decomposition(root, tree): """Generates hierarchical decomposition prompts/completions.""" for c in root.findall('.//'): # Get the immediate parent immediate_parent = c.getparent() # Create a copy of the immediate parent to avoid modifying the original tree parent_snippet_element = copy.deepcopy(immediate_parent) # Remove all children from the copied parent to keep only the parent tag for child in parent_snippet_element: parent_snippet_element.remove(child) # Optionally, add the attributes of the immediate parent to the snippet for key, value in immediate_parent.attrib.items(): parent_snippet_element.set(key, value) # Now convert this modified parent to a string prompt = etree.tostring(parent_snippet_element, pretty_print=True, encoding="UTF-8", xml_declaration=False).decode() # Modification: If c has children, only add the first child to the completion if len(c): # Create a copy of 'c' to avoid modifying the original c_copy = copy.deepcopy(c) # Remove all but the first child from the copy for i in range(len(c_copy) - 1, 0, -1): # Iterate backwards to avoid index issues c_copy.remove(c_copy[i]) parent_snippet_element.insert(0, c_copy) # Add the modified 'c' with only the first child else: parent_snippet_element.insert(0, c) # If 'c' has no children, add it as is completion = etree.tostring(parent_snippet_element, pretty_print=True, encoding="UTF-8", xml_declaration=False).decode() yield prompt, completion # Example usage: tree = etree.parse(<local_path_eadxml_file>) root = tree.getroot() for prompt, completion in hierarchical_decomposition(root, tree): # Pass both root and tree print("Hierarchical content prediction:") print("Prompt:", prompt) print("Completion", completion) print("---") ``` ## Dataset Features The dataset includes the following types of prompt-completion pairs: 1. **Hierarchical Decomposition** - **Prompt**: An XML snippet representing a parent element. - **Completion**: A valid child element that fits within the EAD structure. - **Use Case**: Train models to generate child elements based on their parent context. 2. **Deep Hierarchical Decomposition** - **Prompt**: An XML snippet representing a parent element. - **Completion**: A complete section with deeply nested elements. - **Use Case**: Enable models to predict the relationship between parent and child nodes in XML. 3. **Path-Based Prediction** - **Prompt**: The XPath of a specific EAD/XML element. - **Completion**: The text content of the referenced element. - **Use Case**: Develop models capable of navigating XML trees and retrieving element values. 4. **Masked Element Prediction** - **Prompt**: An XML snippet where a specific element's content is replaced with a mask `[MASK]`. - **Completion**: The original value of the masked element. - **Use Case**: Train models to reconstruct missing information in XML elements. ## Dataset Creation The dataset was created using a set of EAD/XML files. The following steps were followed to generate prompt-completion pairs: 1. **Hierarchical Decomposition** - Parsed the XML tree to isolate `<c>` components and their parents. - Extracted parent elements as prompts and child elements as completions. - Ensured all children were removed from the copied parent to retain context. 2. **Deep Hierarchical Decomposition** - Iterated through focused key EAD/XML sections such as `<eadheader>` or `<archdesc>`. - Recursively parsed the XML tree with a configurable depth (MAX_DEPTH) to control the size and complexity of generated examples - Used the structured template specifying the section to be completed as the prompt and the corresponding extracted XML snippet as the completion. 3. **Path-Based Prediction** - Generated XPath for each element in the XML tree. - Used the XPath as the prompt and the corresponding element's text content as the completion. 4. **Masked Element Prediction** - Masked a specific element's text content in a deep copy of its parent. - Used the masked parent as the prompt and the original text as the completion. Each generated pair was validated for non-empty completions and sanitized to ensure proper formatting and structure. ## Dataset Statistics - **File Source**: EAD/XML files from the French `Inventaires du Catalogue général des manuscrits (CGM)` (BnF) : [https://api.bnf.fr/fr/CCFr/CGM](https://api.bnf.fr/fr/CCFr/CGM). - **Total Samples**: The dataset contains a rich variety of 175 410 examples spanning the four prompt-completion categories. ## Available Datasets Three versions of the dataset are available: * **Ead-Instruct-full-175k:** The complete dataset of 175,000 records. * **[Ead-Instruct-50k](https://huggingface.co/datasets/Geraldine/Ead-Instruct-50k):** A subset of 50,000 records. * **[Ead-Instruct-10k](https://huggingface.co/datasets/Geraldine/Ead-Instruct-10k):** A subset of 10,000 records ## How to Use The dataset can be accessed and used for fine-tuning and evaluating generative models. Prompts and completions are stored as key-value pairs in JSON format. Each entry includes: - `"prompt"`: The input text for the model. - `"completion"`: The expected output from the model. Example entry: ```json { "prompt": "Given this EAD/XML snippet representing a parent element, generate a valid child element that fits within the EAD structure. Snippet: <parent-element>...</parent-element>", "completion": "<child-element>...</child-element>" } ``` ## Applications - **Fine-Tuning**: Train large language models to understand structured XML data. - **XML Autocompletion**: Build tools for EAD/XML editing and validation. - **Information Retrieval**: Develop systems to extract meaningful content from XML archives. - **Data Imputation**: Enhance the capability of models to recover missing or incomplete data. ## Citation If you use this dataset in your research or development, please cite it as follows: ``` @dataset{ead_xml_prompt_completion, title={EAD/XML Dataset for Prompt-Completion Tasks}, author={Géraldine Geoffroy}, year={2024}, publisher={Huggingface Datasets}, url={https://huggingface.co/datasets/Geraldine/Ead-Instruct-full-175k} } ``` ## Acknowledgments This dataset was created using EAD/XML files sourced from the `Inventaires du Catalogue général des manuscrits (CGM)` (BnF) collection.

jasong03/summary-dataset

jasong03

--- dataset_info: features: - name: summary dtype: string splits: - name: train num_bytes: 6672204 num_examples: 27360 download_size: 3553772 dataset_size: 6672204 configs: - config_name: default data_files: - split: train path: data/train-* ---

vinesmsuic/SwissProtCLAP_500k_gpt4o

vinesmsuic

--- dataset_info: features: - name: UniProt ID dtype: string - name: Protein Sequence dtype: string - name: gt_desc dtype: string - name: structure_info dtype: string - name: functional_info dtype: string splits: - name: train num_bytes: 924217773 num_examples: 539563 download_size: 311565954 dataset_size: 924217773 configs: - config_name: default data_files: - split: train path: data/train-* ---

geodevwalid23/palm_tree_dataset

geodevwalid23

--- license: unknown ---

jeongseokoh/GSM8K-Contrastive

jeongseokoh

--- dataset_info: features: - name: question dtype: string - name: past_steps sequence: string - name: answer dtype: string - name: original_question dtype: string - name: original_rp dtype: string - name: negative_steps sequence: string - name: positive_steps dtype: string - name: task dtype: string splits: - name: train num_bytes: 214179460 num_examples: 118058 download_size: 112247393 dataset_size: 214179460 configs: - config_name: default data_files: - split: train path: data/train-* ---

ashercn97/reasoning-v1-small

ashercn97

--- size_categories: n<1K dataset_info: features: - name: anchor dtype: string - name: logical dtype: string - name: illogical dtype: string splits: - name: train num_bytes: 411452 num_examples: 1000 download_size: 248318 dataset_size: 411452 configs: - config_name: default data_files: - split: train path: data/train-* tags: - synthetic - distilabel - rlaif --- <p align="left"> <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> # Dataset Card for reasoning-v1-small This dataset has been created with [distilabel](https://distilabel.argilla.io/). ## Dataset Summary This dataset contains a `pipeline.yaml` which can be used to reproduce the pipeline that generated it in distilabel using the `distilabel` CLI: ```console distilabel pipeline run --config "https://huggingface.co/datasets/ashercn97/reasoning-v1-small/raw/main/pipeline.yaml" ``` or explore the configuration: ```console distilabel pipeline info --config "https://huggingface.co/datasets/ashercn97/reasoning-v1-small/raw/main/pipeline.yaml" ``` ## Dataset structure The examples have the following structure per configuration: <details><summary> Configuration: default </summary><hr> ```json { "anchor": "George wants to warm his hands quickly by rubbing them. Which skin surface will produce the most heat?", "illogical": "Rubbing the back of his hands would be ineffective as it generates less warmth compared to other body parts.", "logical": "The palms of George\u0027s hands will produce the most heat when he rubs them together because they have a higher concentration of blood vessels." } ``` This subset can be loaded as: ```python from datasets import load_dataset ds = load_dataset("ashercn97/reasoning-v1-small", "default") ``` Or simply as it follows, since there's only one configuration and is named `default`: ```python from datasets import load_dataset ds = load_dataset("ashercn97/reasoning-v1-small") ``` </details>

udamaurizio/Google_TTS_Ita_v1

udamaurizio

--- language: - it tags: - audio - tts - text - udanet ---

gokulsrinivasagan/processed_book_corpus_cleaned

gokulsrinivasagan

--- dataset_info: features: - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: special_tokens_mask sequence: int8 splits: - name: train num_bytes: 7023275388.332596 num_examples: 2277342 - name: validation num_bytes: 372257304.0 num_examples: 120706 download_size: 2053364016 dataset_size: 7395532692.332596 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---

ashercn97/reasoning-v2-small

ashercn97

--- size_categories: n<1K dataset_info: features: - name: anchor dtype: string - name: logical dtype: string - name: illogical dtype: string splits: - name: train num_bytes: 562289 num_examples: 1000 download_size: 192324 dataset_size: 562289 configs: - config_name: default data_files: - split: train path: data/train-* tags: - synthetic - distilabel - rlaif --- <p align="left"> <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> # Dataset Card for reasoning-v2-small This dataset has been created with [distilabel](https://distilabel.argilla.io/). ## Dataset Summary This dataset contains a `pipeline.yaml` which can be used to reproduce the pipeline that generated it in distilabel using the `distilabel` CLI: ```console distilabel pipeline run --config "https://huggingface.co/datasets/ashercn97/reasoning-v2-small/raw/main/pipeline.yaml" ``` or explore the configuration: ```console distilabel pipeline info --config "https://huggingface.co/datasets/ashercn97/reasoning-v2-small/raw/main/pipeline.yaml" ``` ## Dataset structure The examples have the following structure per configuration: <details><summary> Configuration: default </summary><hr> ```json { "anchor": "If a poppy is boring and red, then the poppy is big.\nIf a poppy is fast, then the poppy is weak.\nIf a poppy is smart or hot, then the poppy is good.\nIf a poppy is purple, then the poppy is bad.\nIf a poppy is beautiful and strong, then the poppy is soft.\nFact:\nThe poppy is beautiful and hot.\nThe following can be determined about the poppy:", "illogical": "If a poppy is boring and weak, then the poppy is small.", "logical": "Given that the poppy is beautiful and hot, we can conclude that the poppy is good." } ``` This subset can be loaded as: ```python from datasets import load_dataset ds = load_dataset("ashercn97/reasoning-v2-small", "default") ``` Or simply as it follows, since there's only one configuration and is named `default`: ```python from datasets import load_dataset ds = load_dataset("ashercn97/reasoning-v2-small") ``` </details>

Samoed/IndicCrosslingualSTS

Samoed

--- dataset_info: - config_name: en-as features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 60945 num_examples: 256 download_size: 35376 dataset_size: 60945 - config_name: en-bn features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 67460 num_examples: 256 download_size: 38088 dataset_size: 67460 - config_name: en-gu features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 64786 num_examples: 256 download_size: 37140 dataset_size: 64786 - config_name: en-hi features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 92497 num_examples: 256 download_size: 51498 dataset_size: 92497 - config_name: en-kn features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 77385 num_examples: 256 download_size: 42987 dataset_size: 77385 - config_name: en-ml features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 79979 num_examples: 256 download_size: 44196 dataset_size: 79979 - config_name: en-mr features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 75928 num_examples: 256 download_size: 43383 dataset_size: 75928 - config_name: en-or features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 57794 num_examples: 256 download_size: 32315 dataset_size: 57794 - config_name: en-pa features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 75532 num_examples: 256 download_size: 43175 dataset_size: 75532 - config_name: en-ta features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 87284 num_examples: 256 download_size: 43472 dataset_size: 87284 - config_name: en-te features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 79011 num_examples: 256 download_size: 43790 dataset_size: 79011 - config_name: en-ur features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 72395 num_examples: 256 download_size: 46115 dataset_size: 72395 configs: - config_name: en-as data_files: - split: test path: en-as/test-* - config_name: en-bn data_files: - split: test path: en-bn/test-* - config_name: en-gu data_files: - split: test path: en-gu/test-* - config_name: en-hi data_files: - split: test path: en-hi/test-* - config_name: en-kn data_files: - split: test path: en-kn/test-* - config_name: en-ml data_files: - split: test path: en-ml/test-* - config_name: en-mr data_files: - split: test path: en-mr/test-* - config_name: en-or data_files: - split: test path: en-or/test-* - config_name: en-pa data_files: - split: test path: en-pa/test-* - config_name: en-ta data_files: - split: test path: en-ta/test-* - config_name: en-te data_files: - split: test path: en-te/test-* - config_name: en-ur data_files: - split: test path: en-ur/test-* ---

plaguss/math_shepherd_token

plaguss

--- dataset_info: features: - name: prompt dtype: string - name: completions sequence: string - name: labels sequence: bool splits: - name: train num_bytes: 368155117 num_examples: 422422 - name: test num_bytes: 19423237 num_examples: 22233 download_size: 195393521 dataset_size: 387578354 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

kawsarahmd/english_bangla_nmt_datasets_bidirectional_v2

kawsarahmd

--- dataset_info: features: - name: id dtype: string - name: news_id dtype: string - name: input_text dtype: string - name: output_text dtype: string splits: - name: train num_bytes: 326584767 num_examples: 105600 - name: validation num_bytes: 28094694 num_examples: 9387 - name: test num_bytes: 7209579 num_examples: 2347 download_size: 172182902 dataset_size: 361889040 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* ---

jacobmorrison/tulu-3-sft-single-turn

jacobmorrison

--- dataset_info: features: - name: id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: source dtype: string splits: - name: train num_bytes: 2388461728 num_examples: 939343 download_size: 1152053521 dataset_size: 2388461728 configs: - config_name: default data_files: - split: train path: data/train-* ---

ayoubsa/Sign_Road_Detection_Dataset

ayoubsa

--- license: cc task_categories: - object-detection language: - en size_categories: - 1K<n<10K --- # Dataset Description <!-- Provide a quick summary of the dataset. --> The dataset contains images of road signs with annotations in YOLO format, which specify the class ID and the bounding box coordinates for each object. There are 15 classes: - Traffic Lights: Green Light, Red Light. - Speed Limits: 10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120. - Stop Sign: Stop. Each image can contain multiple road signs. The dataset simulates real-world driving conditions, including varying weather, lighting, and road environments. # Dataset Usage You can use this dataset to detect different road signs. This is a link for my competition leaderboard in colab where you can submit your results: https://codalab.lisn.upsaclay.fr/competitions/21061#results # Authors Provided by a Roboflow user. # License CC BY 4.0.

nlv23/earlymodernspanishonchina

nlv23

--- license: cc-by-nc-3.0 ---

ernestchu/emnist-digits

ernestchu

--- dataset_info: features: - name: image dtype: image - name: label dtype: int64 splits: - name: train num_bytes: 102459463.0 num_examples: 240000 - name: test num_bytes: 17074672.0 num_examples: 40000 download_size: 371539854 dataset_size: 119534135.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

mk43275/combined_diary

mk43275

--- license: mit ---

kornwtp/en-stsbenchmark-sts

kornwtp

--- license: apache-2.0 ---

naufalso/owasp_top10_2017_2021

naufalso

--- dataset_info: features: - name: title dtype: string - name: path dtype: string - name: text dtype: string - name: total_chars dtype: int64 - name: file_size_mb dtype: float64 - name: text_w_embed_image dtype: string splits: - name: train num_bytes: 2623829 num_examples: 39 download_size: 2487903 dataset_size: 2623829 configs: - config_name: default data_files: - split: train path: data/train-* ---

linyongj/eval_so100_act

linyongj

--- task_categories: - robotics tags: - LeRobot - so100 - tutorial --- This dataset was created using [LeRobot](https://github.com/huggingface/lerobot).

udamaurizio/parler_Google_TTS_Ita_v1_prompted

udamaurizio

--- language: - it dataset_info: features: - name: text dtype: string - name: transcription_normalised dtype: string - name: utterance_pitch_mean dtype: float32 - name: utterance_pitch_std dtype: float32 - name: snr dtype: float64 - name: c50 dtype: float64 - name: speaking_rate dtype: string - name: phonemes dtype: string - name: noise dtype: string - name: reverberation dtype: string - name: speech_monotony dtype: string - name: text_description dtype: string splits: - name: train num_bytes: 28361 num_examples: 68 download_size: 18871 dataset_size: 28361 configs: - config_name: default data_files: - split: train path: data/train-* license: apache-2.0 tags: - tts size_categories: - n<1K ---

rmsdud/chat

rmsdud

--- dataset_info: features: - name: context dtype: string - name: response dtype: string splits: - name: train num_bytes: 3753161 num_examples: 23263 download_size: 1554612 dataset_size: 3753161 configs: - config_name: default data_files: - split: train path: data/train-* ---

SaltyCedar/Copus_pat2011_forSP

SaltyCedar

--- license: apache-2.0 ---

jkazdan/pku-safe-30k-test-Mistral-7B-Instruct-v0.2

jkazdan

--- dataset_info: features: - name: prompt dtype: string - name: response dtype: string splits: - name: train num_bytes: 2641924 num_examples: 2816 download_size: 1362334 dataset_size: 2641924 configs: - config_name: default data_files: - split: train path: data/train-* ---