Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,601 @@
+---
+base_model: google/electra-large-discriminator
+datasets:
+- PiC/phrase_similarity
+language:
+- en
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- manhattan_accuracy
+- manhattan_accuracy_threshold
+- manhattan_f1
+- manhattan_f1_threshold
+- manhattan_precision
+- manhattan_recall
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_accuracy_threshold
+- euclidean_f1
+- euclidean_f1_threshold
+- euclidean_precision
+- euclidean_recall
+- euclidean_ap
+- max_accuracy
+- max_accuracy_threshold
+- max_f1
+- max_f1_threshold
+- max_precision
+- max_recall
+- max_ap
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:7004
+- loss:SoftmaxLoss
+widget:
+- source_sentence: Google SEO expert Matt Cutts had a similar experience, of the eight
+    magazines and newspapers Cutts tried to order, he received zero.
+  sentences:
+  - He dissolved the services of her guards and her court attendants and seized an
+    expansive reach of properties belonging to her.
+  - Google SEO expert Matt Cutts had a comparable occurrence, of the eight magazines
+    and newspapers Cutts tried to order, he received zero.
+  - bill's newest solo play, "all over the map", premiered off broadway in april 2016,
+    produced by all for an individual cinema.
+- source_sentence: Shula said that Namath "beat our blitz" with his fast release,
+    which let him quickly dump the football off to a receiver.
+  sentences:
+  - Shula said that Namath "beat our blitz" with his quick throw, which let him quickly
+    dump the football off to a receiver.
+  - it elects a single component of parliament (mp) by the first past the post system
+    of election.
+  - Matt Groening said that West was one of the most widely known group to ever come
+    to the studio.
+- source_sentence: When Angel calls out her name, Cordelia suddenly appears from the
+    opposite side of the room saying, "Yep, that chick's in rough shape.
+  sentences:
+  - The ruined row of text, part of the Florida East Coast Railway, was repaired by
+    2014 renewing freight train access to the port.
+  - When Angel calls out her name, Cordelia suddenly appears from the opposite side
+    of the room saying, "Yep, that chick's in approximate form.
+  - Chaplin's films introduced a moderated kind of comedy than the typical Keystone
+    farce, and he developed a large fan base.
+- source_sentence: The following table shows the distances traversed by National Route
+    11 in each different department, showing cities and towns that it passes by (or
+    near).
+  sentences:
+  - The following table shows the distances traversed by National Route 11 in each
+    separate city authority, showing cities and towns that it passes by (or near).
+  - Similarly, indigenous communities and leaders practice as the main rule of law
+    on local native lands and reserves.
+  - later, sylvan mixed gary numan's albums "replicas" (with numan's previous band
+    tubeway army) and "the quest for instant gratification".
+- source_sentence: She wants to write about Keima but suffers a major case of writer's
+    block.
+  sentences:
+  - In some countries, new extremist parties on the extreme opposite of left of the
+    political spectrum arose, motivated through issues of immigration, multiculturalism
+    and integration.
+  - specific medical status of movement and the general condition of movement both
+    are conditions under which contradictions can move.
+  - She wants to write about Keima but suffers a huge occurrence of writer's block.
+model-index:
+- name: SentenceTransformer based on google/electra-large-discriminator
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: quora duplicates dev
+      type: quora-duplicates-dev
+    metrics:
+    - type: cosine_accuracy
+      value: 0.748
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.9737387895584106
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.7604846225535881
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.9574624300003052
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.7120418848167539
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.816
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.786909093121924
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.667
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 275.4551696777344
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.733229329173167
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 266.14727783203125
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.6010230179028133
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.94
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.5935392159238977
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.746
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 87.73857116699219
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.7614678899082568
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 131.43374633789062
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.7033898305084746
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.83
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.7904964653279406
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.747
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 4.5833892822265625
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.7610121836925962
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 5.5540361404418945
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.7160493827160493
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.812
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.789806008641207
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.748
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 275.4551696777344
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.7614678899082568
+      name: Max F1
+    - type: max_f1_threshold
+      value: 266.14727783203125
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.7160493827160493
+      name: Max Precision
+    - type: max_recall
+      value: 0.94
+      name: Max Recall
+    - type: max_ap
+      value: 0.7904964653279406
+      name: Max Ap
+---
+
+# SentenceTransformer based on google/electra-large-discriminator
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google/electra-large-discriminator](https://huggingface.co/google/electra-large-discriminator) on the [PiC/phrase_similarity](https://huggingface.co/datasets/PiC/phrase_similarity) dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [google/electra-large-discriminator](https://huggingface.co/google/electra-large-discriminator) <!-- at revision c13c3df7efadc2162f42588bd28eb4e187d602a5 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [PiC/phrase_similarity](https://huggingface.co/datasets/PiC/phrase_similarity)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: ElectraModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("Deehan1866/Electra")
+# Run inference
+sentences = [
+    "She wants to write about Keima but suffers a major case of writer's block.",
+    "She wants to write about Keima but suffers a huge occurrence of writer's block.",
+    'specific medical status of movement and the general condition of movement both are conditions under which contradictions can move.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Binary Classification
+* Dataset: `quora-duplicates-dev`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.748      |
+| cosine_accuracy_threshold    | 0.9737     |
+| cosine_f1                    | 0.7605     |
+| cosine_f1_threshold          | 0.9575     |
+| cosine_precision             | 0.712      |
+| cosine_recall                | 0.816      |
+| cosine_ap                    | 0.7869     |
+| dot_accuracy                 | 0.667      |
+| dot_accuracy_threshold       | 275.4552   |
+| dot_f1                       | 0.7332     |
+| dot_f1_threshold             | 266.1473   |
+| dot_precision                | 0.601      |
+| dot_recall                   | 0.94       |
+| dot_ap                       | 0.5935     |
+| manhattan_accuracy           | 0.746      |
+| manhattan_accuracy_threshold | 87.7386    |
+| manhattan_f1                 | 0.7615     |
+| manhattan_f1_threshold       | 131.4337   |
+| manhattan_precision          | 0.7034     |
+| manhattan_recall             | 0.83       |
+| manhattan_ap                 | 0.7905     |
+| euclidean_accuracy           | 0.747      |
+| euclidean_accuracy_threshold | 4.5834     |
+| euclidean_f1                 | 0.761      |
+| euclidean_f1_threshold       | 5.554      |
+| euclidean_precision          | 0.716      |
+| euclidean_recall             | 0.812      |
+| euclidean_ap                 | 0.7898     |
+| max_accuracy                 | 0.748      |
+| max_accuracy_threshold       | 275.4552   |
+| max_f1                       | 0.7615     |
+| max_f1_threshold             | 266.1473   |
+| max_precision                | 0.716      |
+| max_recall                   | 0.94       |
+| **max_ap**                   | **0.7905** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### PiC/phrase_similarity
+
+* Dataset: [PiC/phrase_similarity](https://huggingface.co/datasets/PiC/phrase_similarity) at [fc67ce7](https://huggingface.co/datasets/PiC/phrase_similarity/tree/fc67ce7c1e69e360e42dc6f31ddf97bb32f1923d)
+* Size: 7,004 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                          | sentence2                                                                          | label                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | int                                             |
+  | details | <ul><li>min: 12 tokens</li><li>mean: 26.35 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 12 tokens</li><li>mean: 26.89 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>0: ~48.80%</li><li>1: ~51.20%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                 | sentence2                                                                                                                                        | label          |
+  |:------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>newly formed camp is released from the membrane and diffuses across the intracellular space where it serves to activate pka.</code> | <code>recently made encampment is released from the membrane and diffuses across the intracellular space where it serves to activate pka.</code> | <code>0</code> |
+  | <code>According to one data, in 1910, on others – in 1915, the mansion became Natalya Dmitriyevna Shchuchkina's property.</code>          | <code>According to a particular statistic, in 1910, on others – in 1915, the mansion became Natalya Dmitriyevna Shchuchkina's property.</code>   | <code>1</code> |
+  | <code>Note that Fact 1 does not assume any particular structure on the set formula_65.</code>                                             | <code>Note that Fact 1 does not assume any specific edifice on the set formula_65.</code>                                                        | <code>0</code> |
+* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
+
+### Evaluation Dataset
+
+#### PiC/phrase_similarity
+
+* Dataset: [PiC/phrase_similarity](https://huggingface.co/datasets/PiC/phrase_similarity) at [fc67ce7](https://huggingface.co/datasets/PiC/phrase_similarity/tree/fc67ce7c1e69e360e42dc6f31ddf97bb32f1923d)
+* Size: 1,000 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 9 tokens</li><li>mean: 26.21 tokens</li><li>max: 61 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 26.8 tokens</li><li>max: 61 tokens</li></ul> | <ul><li>0: ~50.00%</li><li>1: ~50.00%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                   | sentence2                                                                                                                     | label          |
+  |:----------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>after theo's apparent death, she decides to leave first colony and ends up traveling with the apostles.</code>        | <code>after theo's apparent death, she decides to leave original settlement and ends up traveling with the apostles.</code>   | <code>0</code> |
+  | <code>The guard assigned to Vivian leaves her to prevent the robbery, allowing her to connect to the bank's network.</code> | <code>The guard assigned to Vivian leaves her to prevent the robbery, allowing her to connect to the bank's locations.</code> | <code>0</code> |
+  | <code>Two days later Louis XVI banished Necker by a "lettre de cachet" for his very public exchange of pamphlets.</code>    | <code>Two days later Louis XVI banished Necker by a "lettre de cachet" for his very free forum of pamphlets.</code>           | <code>0</code> |
+* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `load_best_model_at_end`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step    | Training Loss | loss       | quora-duplicates-dev_max_ap |
+|:----------:|:-------:|:-------------:|:----------:|:---------------------------:|
+| 0          | 0       | -             | -          | 0.6721                      |
+| 0.2283     | 100     | -             | 0.6805     | 0.6847                      |
+| **0.4566** | **200** | **-**         | **0.5313** | **0.7905**                  |
+| 0.6849     | 300     | -             | 0.5383     | 0.7838                      |
+| 0.9132     | 400     | -             | 0.6442     | 0.7585                      |
+| 1.1416     | 500     | 0.5761        | 0.5742     | 0.7843                      |
+| 1.3699     | 600     | -             | 0.5606     | 0.7558                      |
+| 1.5982     | 700     | -             | 0.5716     | 0.7772                      |
+| 1.8265     | 800     | -             | 0.5573     | 0.7619                      |
+| 2.0548     | 900     | -             | 0.6951     | 0.7760                      |
+| 2.2831     | 1000    | 0.3712        | 0.7678     | 0.7753                      |
+| 2.5114     | 1100    | -             | 0.7712     | 0.7915                      |
+| 2.7397     | 1200    | -             | 0.8120     | 0.7914                      |
+| 2.9680     | 1300    | -             | 0.8045     | 0.7789                      |
+| 3.1963     | 1400    | -             | 0.9936     | 0.7821                      |
+| 3.4247     | 1500    | 0.1942        | 1.0883     | 0.7679                      |
+| 3.6530     | 1600    | -             | 0.9814     | 0.7566                      |
+| 3.8813     | 1700    | -             | 1.0897     | 0.7830                      |
+| 4.1096     | 1800    | -             | 1.0764     | 0.7729                      |
+| 4.3379     | 1900    | -             | 1.1209     | 0.7802                      |
+| 4.5662     | 2000    | 0.1175        | 1.1522     | 0.7804                      |
+| 4.7945     | 2100    | -             | 1.1545     | 0.7807                      |
+| 5.0        | 2190    | -             | -          | 0.7905                      |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.10
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.3
+- PyTorch: 2.2.1+cu121
+- Accelerate: 0.32.1
+- Datasets: 2.20.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers and SoftmaxLoss
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "google/electra-large-discriminator",
+  "architectures": [
+    "ElectraModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 1024,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.3",
+    "pytorch": "2.2.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170ef32b7e718a9992f87bf9957c7fb14b15e6fe2bb743094a0ac8fa746ff9ad
+size 1336413848

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}