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 +1,593 @@
+---
+base_model: sileod/deberta-v3-large-tasksource-nli
+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: The valve will open 100% when the set point is reached and will
+    remain open until a certain blow down factor is reached.
+  sentences:
+  - Having raised $17,000,000 in a standard matter, one of the first speculative IPOs,
+    Tucker needed more money to continue development of the car.
+  - The valve will open 100% when the tennis scoring protocol is reached and will
+    remain open until a certain blow down factor is reached.
+  - But the government of PML (N) gave it the complete exponential of a Tehsil.
+- source_sentence: Java BluePrints was the first source to promote Model View Controller
+    (MVC) and Data Access Object (DAO) for Java EE application development.
+  sentences:
+  - Java BluePrints was the pioneer authority to promote Model View Controller (MVC)
+    and Data Access Object (DAO) for Java EE application development.
+  - One of the primary job of IIUG is to publish news through a monthly newsletter
+    ("The Insider").
+  - Opera Dragonfly must be downloaded on original practice, and functions offline
+    thereafter.
+- source_sentence: It also appears immediately after the first shower of the monsoon.
+  sentences:
+  - The latter can be minimised by meticulous precision to the wheel bearings, tyre
+    sizes and pressures, and brakes (to avoid parasitic brake drag).
+  - It also appears immediately after the initial rain of the monsoon.
+  - McCullough filed a second appeal that could not be denied without a hearing from
+    the State Attorney's Office.
+- source_sentence: This type places the shifters closer to the hand positions, but
+    still offer a simple reliable system, especially for touring cyclist.
+  sentences:
+  - This type places the shifters closer to the palm placement, but still offer a
+    simple reliable system, especially for touring cyclist.
+  - All square dancers learn standard "definitions" of calls, which they recall and
+    use when the caller issues a certain directive.
+  - Mainos-TV operated by leasing atmospheric duration from Yleisradio, broadcasting
+    in reserved blocks between Yleisradio's own programming on its two channels.
+- source_sentence: He also played with the Turkish 2nd Division team Pertevniyal,
+    which was at the time the farm team of Efes, via a dual license.
+  sentences:
+  - The group is still active, producing a monthly action points on the women, peace,
+    and authentication blocks affecting countries on Council's agenda.
+  - 'Storage/centre tracks are found in the vicinity of the following stations:
+
+    Other song highlights.'
+  - He also played with the Turkish 2nd Division team Pertevniyal, which was at the
+    time the farm team of Efes, via a two-part authorization.
+model-index:
+- name: SentenceTransformer based on sileod/deberta-v3-large-tasksource-nli
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: quora duplicates dev
+      type: quora-duplicates-dev
+    metrics:
+    - type: cosine_accuracy
+      value: 0.753
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.8562747240066528
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.7734303912647863
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.827180027961731
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.7095158597662772
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.85
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.7593865167351814
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.716
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 472.6572265625
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.7501982553528945
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 343.77313232421875
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.621550591327201
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.946
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.6945003367753116
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.754
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 320.8356018066406
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.7716105550500454
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 356.869140625
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.7078464106844741
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.848
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.75919098072954
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.751
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 13.484582901000977
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.7697777777777778
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 15.105815887451172
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.6928
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.866
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.7572975810714628
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.754
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 472.6572265625
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.7734303912647863
+      name: Max F1
+    - type: max_f1_threshold
+      value: 356.869140625
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.7095158597662772
+      name: Max Precision
+    - type: max_recall
+      value: 0.946
+      name: Max Recall
+    - type: max_ap
+      value: 0.7593865167351814
+      name: Max Ap
+---
+
+# SentenceTransformer based on sileod/deberta-v3-large-tasksource-nli
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sileod/deberta-v3-large-tasksource-nli](https://huggingface.co/sileod/deberta-v3-large-tasksource-nli) 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:** [sileod/deberta-v3-large-tasksource-nli](https://huggingface.co/sileod/deberta-v3-large-tasksource-nli) <!-- at revision 212de447184bda8fb9415a2e5697846864ddf304 -->
+- **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: DebertaV2Model 
+  (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/finetuned-valloss-sileod-deberta-v3-large-tasksource-nli")
+# Run inference
+sentences = [
+    'He also played with the Turkish 2nd Division team Pertevniyal, which was at the time the farm team of Efes, via a dual license.',
+    'He also played with the Turkish 2nd Division team Pertevniyal, which was at the time the farm team of Efes, via a two-part authorization.',
+    'Storage/centre tracks are found in the vicinity of the following stations:\nOther song highlights.',
+]
+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              | 0.753      |
+| cosine_accuracy_threshold    | 0.8563     |
+| cosine_f1                    | 0.7734     |
+| cosine_f1_threshold          | 0.8272     |
+| cosine_precision             | 0.7095     |
+| cosine_recall                | 0.85       |
+| cosine_ap                    | 0.7594     |
+| dot_accuracy                 | 0.716      |
+| dot_accuracy_threshold       | 472.6572   |
+| dot_f1                       | 0.7502     |
+| dot_f1_threshold             | 343.7731   |
+| dot_precision                | 0.6216     |
+| dot_recall                   | 0.946      |
+| dot_ap                       | 0.6945     |
+| manhattan_accuracy           | 0.754      |
+| manhattan_accuracy_threshold | 320.8356   |
+| manhattan_f1                 | 0.7716     |
+| manhattan_f1_threshold       | 356.8691   |
+| manhattan_precision          | 0.7078     |
+| manhattan_recall             | 0.848      |
+| manhattan_ap                 | 0.7592     |
+| euclidean_accuracy           | 0.751      |
+| euclidean_accuracy_threshold | 13.4846    |
+| euclidean_f1                 | 0.7698     |
+| euclidean_f1_threshold       | 15.1058    |
+| euclidean_precision          | 0.6928     |
+| euclidean_recall             | 0.866      |
+| euclidean_ap                 | 0.7573     |
+| max_accuracy                 | 0.754      |
+| max_accuracy_threshold       | 472.6572   |
+| max_f1                       | 0.7734     |
+| max_f1_threshold             | 356.8691   |
+| max_precision                | 0.7095     |
+| max_recall                   | 0.946      |
+| **max_ap**                   | **0.7594** |
+
+<!--
+## 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: 25.5 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 12 tokens</li><li>mean: 25.9 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: 10 tokens</li><li>mean: 25.46 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 25.84 tokens</li><li>max: 59 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`: 100
+- `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`: 100
+- `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       | -             | -          | 0.6829                      |
+| 0.2283     | 100     | -             | 0.6795     | 0.6829                      |
+| 0.4566     | 200     | -             | 0.6664     | 0.6873                      |
+| 0.6849     | 300     | -             | 0.6426     | 0.7011                      |
+| 0.9132     | 400     | -             | 0.5995     | 0.7190                      |
+| 1.1416     | 500     | 0.6452        | 0.5537     | 0.7410                      |
+| 1.3699     | 600     | -             | 0.5262     | 0.7525                      |
+| **1.5982** | **700** | **-**         | **0.5199** | **0.7594**                  |
+| 1.8265     | 800     | -             | 0.5206     | 0.7655                      |
+| 2.0548     | 900     | -             | 0.5340     | 0.7745                      |
+| 2.2831     | 1000    | 0.4654        | 0.5433     | 0.7790                      |
+| 2.5114     | 1100    | -             | 0.5683     | 0.7728                      |
+| 2.7397     | 1200    | -             | 0.5629     | 0.7774                      |
+| 2.9680     | 1300    | -             | 0.5715     | 0.7732                      |
+| 3.1963     | 1400    | -             | 0.6772     | 0.7777                      |
+| 3.4247     | 1500    | 0.3219        | 0.6834     | 0.7844                      |
+| 3.6530     | 1600    | -             | 0.7428     | 0.7792                      |
+| 3.8813     | 1700    | -             | 0.7353     | 0.7594                      |
+
+* 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.*
+-->

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,1077 @@
+{
+  "_name_or_path": "sileod/deberta-v3-large-tasksource-nli",
+  "architectures": [
+    "DebertaV2Model"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifiers_size": [
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    1,
+    2,
+    3,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    1,
+    3,
+    3,
+    2,
+    2,
+    3,
+    2,
+    2,
+    2,
+    6,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2,
+    2,
+    2,
+    5,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2,
+    2,
+    2,
+    47,
+    23,
+    9,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    20,
+    50,
+    3,
+    3,
+    4,
+    2,
+    8,
+    3,
+    2,
+    20,
+    4,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    3,
+    174,
+    2,
+    41,
+    51,
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    2,
+    3,
+    16,
+    2,
+    2,
+    2,
+    8,
+    18,
+    2,
+    17,
+    42,
+    7,
+    3,
+    12,
+    7,
+    4,
+    11,
+    3,
+    100,
+    13,
+    100,
+    8,
+    1,
+    20,
+    2,
+    2,
+    4,
+    5,
+    3,
+    4,
+    14,
+    2,
+    6,
+    4,
+    2,
+    1,
+    3,
+    10,
+    3,
+    10,
+    4,
+    2,
+    7,
+    6,
+    28,
+    3,
+    6,
+    5,
+    7,
+    3,
+    6,
+    4,
+    2,
+    7,
+    2,
+    2,
+    2,
+    2,
+    6,
+    20,
+    2,
+    9,
+    13,
+    4,
+    3,
+    3,
+    2,
+    4,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    4,
+    1,
+    2,
+    1,
+    13,
+    3,
+    5,
+    11,
+    37,
+    2,
+    49,
+    40,
+    10,
+    4,
+    1,
+    2,
+    2,
+    1,
+    5,
+    2,
+    3,
+    2,
+    2,
+    12,
+    3,
+    3,
+    2,
+    19,
+    3,
+    1,
+    2,
+    2,
+    2,
+    2,
+    2,
+    1,
+    2,
+    2,
+    1,
+    1,
+    2,
+    3,
+    2,
+    1,
+    4,
+    3,
+    1,
+    1,
+    1,
+    2,
+    3,
+    2,
+    3,
+    1,
+    1,
+    2,
+    1,
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    2,
+    2,
+    2,
+    1,
+    3,
+    2,
+    2,
+    1,
+    1,
+    1,
+    1,
+    2,
+    1,
+    1,
+    1,
+    1,
+    4,
+    1,
+    1,
+    1,
+    1,
+    3,
+    1,
+    3,
+    1,
+    2,
+    2,
+    1,
+    2,
+    3,
+    3,
+    2,
+    1,
+    3,
+    1,
+    1,
+    3,
+    1,
+    3,
+    2,
+    1,
+    1,
+    1,
+    2,
+    50,
+    50,
+    50,
+    50,
+    2,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    2,
+    2,
+    2,
+    2,
+    77,
+    1,
+    3,
+    2,
+    2,
+    1,
+    1,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    18,
+    13,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    4,
+    2,
+    24,
+    23,
+    67,
+    279,
+    3,
+    2,
+    2,
+    1,
+    2,
+    2,
+    3,
+    1,
+    2,
+    3,
+    2,
+    3,
+    3,
+    2,
+    2,
+    4,
+    1,
+    17,
+    3,
+    2,
+    3,
+    2,
+    3,
+    3,
+    2,
+    1,
+    1,
+    3,
+    2,
+    9,
+    2,
+    1,
+    1,
+    1,
+    1,
+    1,
+    2,
+    2,
+    3,
+    2,
+    3,
+    4,
+    2,
+    3,
+    3,
+    3,
+    1,
+    1
+  ],
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "tasks": [
+    "glue/mnli",
+    "glue/qnli",
+    "glue/rte",
+    "glue/wnli",
+    "glue/mrpc",
+    "glue/qqp",
+    "glue/stsb",
+    "super_glue/boolq",
+    "super_glue/cb",
+    "super_glue/multirc",
+    "super_glue/wic",
+    "super_glue/axg",
+    "anli/a1",
+    "anli/a2",
+    "anli/a3",
+    "sick/label",
+    "sick/relatedness",
+    "sick/entailment_AB",
+    "snli",
+    "scitail/snli_format",
+    "hans",
+    "WANLI",
+    "recast/recast_megaveridicality",
+    "recast/recast_sentiment",
+    "recast/recast_verbnet",
+    "recast/recast_kg_relations",
+    "recast/recast_puns",
+    "recast/recast_factuality",
+    "recast/recast_verbcorner",
+    "recast/recast_ner",
+    "probability_words_nli/usnli",
+    "probability_words_nli/reasoning_1hop",
+    "probability_words_nli/reasoning_2hop",
+    "nan-nli/joey234--nan-nli",
+    "nli_fever",
+    "breaking_nli",
+    "conj_nli",
+    "fracas",
+    "dialogue_nli",
+    "mpe",
+    "dnc",
+    "recast_white/fnplus",
+    "recast_white/sprl",
+    "recast_white/dpr",
+    "joci",
+    "robust_nli/IS_CS",
+    "robust_nli/LI_LI",
+    "robust_nli/ST_WO",
+    "robust_nli/PI_SP",
+    "robust_nli/PI_CD",
+    "robust_nli/ST_SE",
+    "robust_nli/ST_NE",
+    "robust_nli/ST_LM",
+    "robust_nli_is_sd",
+    "robust_nli_li_ts",
+    "add_one_rte",
+    "imppres/implicature_gradable_adjective/log",
+    "imppres/implicature_numerals_2_3/log",
+    "imppres/implicature_modals/log",
+    "imppres/implicature_gradable_verb/log",
+    "imppres/implicature_numerals_10_100/log",
+    "imppres/implicature_quantifiers/log",
+    "imppres/implicature_connectives/log",
+    "glue_diagnostics/diagnostics",
+    "hlgd",
+    "paws/labeled_final",
+    "paws/labeled_swap",
+    "medical_questions_pairs",
+    "conll2003/pos_tags",
+    "conll2003/chunk_tags",
+    "conll2003/ner_tags",
+    "model-written-evals",
+    "truthful_qa/multiple_choice",
+    "fig-qa",
+    "bigbench/tracking_shuffled_objects",
+    "bigbench/color",
+    "bigbench/cause_and_effect",
+    "bigbench/dyck_languages",
+    "bigbench/identify_math_theorems",
+    "bigbench/unit_interpretation",
+    "bigbench/arithmetic",
+    "bigbench/social_iqa",
+    "bigbench/penguins_in_a_table",
+    "bigbench/play_dialog_same_or_different",
+    "bigbench/novel_concepts",
+    "bigbench/international_phonetic_alphabet_nli",
+    "bigbench/implicatures",
+    "bigbench/english_proverbs",
+    "bigbench/simple_ethical_questions",
+    "bigbench/sports_understanding",
+    "bigbench/emoji_movie",
+    "bigbench/implicit_relations",
+    "bigbench/empirical_judgments",
+    "bigbench/navigate",
+    "bigbench/logical_deduction",
+    "bigbench/reasoning_about_colored_objects",
+    "bigbench/snarks",
+    "bigbench/gre_reading_comprehension",
+    "bigbench/ruin_names",
+    "bigbench/analytic_entailment",
+    "bigbench/authorship_verification",
+    "bigbench/code_line_description",
+    "bigbench/logical_sequence",
+    "bigbench/disambiguation_qa",
+    "bigbench/misconceptions",
+    "bigbench/understanding_fables",
+    "bigbench/intent_recognition",
+    "bigbench/odd_one_out",
+    "bigbench/temporal_sequences",
+    "bigbench/analogical_similarity",
+    "bigbench/emojis_emotion_prediction",
+    "bigbench/key_value_maps",
+    "bigbench/identify_odd_metaphor",
+    "bigbench/geometric_shapes",
+    "bigbench/suicide_risk",
+    "bigbench/strategyqa",
+    "bigbench/logical_fallacy_detection",
+    "bigbench/known_unknowns",
+    "bigbench/social_support",
+    "bigbench/logic_grid_puzzle",
+    "bigbench/question_selection",
+    "bigbench/fact_checker",
+    "bigbench/moral_permissibility",
+    "bigbench/dark_humor_detection",
+    "bigbench/mathematical_induction",
+    "bigbench/movie_recommendation",
+    "bigbench/human_organs_senses",
+    "bigbench/vitaminc_fact_verification",
+    "bigbench/movie_dialog_same_or_different",
+    "bigbench/metaphor_boolean",
+    "bigbench/causal_judgment",
+    "bigbench/epistemic_reasoning",
+    "bigbench/sentence_ambiguity",
+    "bigbench/logical_args",
+    "bigbench/hindu_knowledge",
+    "bigbench/cs_algorithms",
+    "bigbench/hhh_alignment",
+    "bigbench/physical_intuition",
+    "bigbench/crash_blossom",
+    "bigbench/cifar10_classification",
+    "bigbench/riddle_sense",
+    "bigbench/hyperbaton",
+    "bigbench/general_knowledge",
+    "bigbench/anachronisms",
+    "bigbench/entailed_polarity",
+    "bigbench/nonsense_words_grammar",
+    "bigbench/mnist_ascii",
+    "bigbench/symbol_interpretation",
+    "bigbench/figure_of_speech_detection",
+    "bigbench/abstract_narrative_understanding",
+    "bigbench/irony_identification",
+    "bigbench/discourse_marker_prediction",
+    "bigbench/date_understanding",
+    "bigbench/metaphor_understanding",
+    "bigbench/goal_step_wikihow",
+    "bigbench/similarities_abstraction",
+    "bigbench/salient_translation_error_detection",
+    "bigbench/formal_fallacies_syllogisms_negation",
+    "bigbench/presuppositions_as_nli",
+    "bigbench/fantasy_reasoning",
+    "bigbench/contextual_parametric_knowledge_conflicts",
+    "bigbench/evaluating_information_essentiality",
+    "bigbench/real_or_fake_text",
+    "bigbench/conceptual_combinations",
+    "bigbench/phrase_relatedness",
+    "bigbench/crass_ai",
+    "bigbench/undo_permutation",
+    "bigbench/physics",
+    "bigbench/timedial",
+    "bigbench/winowhy",
+    "bigbench/checkmate_in_one",
+    "bigbench/bbq_lite_json",
+    "bigbench/strange_stories",
+    "bigbench/elementary_math_qa",
+    "cos_e/v1.0",
+    "cosmos_qa",
+    "dream",
+    "openbookqa",
+    "qasc",
+    "quartz",
+    "quail",
+    "head_qa/en",
+    "sciq",
+    "social_i_qa",
+    "wiki_hop/original",
+    "wiqa",
+    "piqa",
+    "hellaswag",
+    "super_glue/copa",
+    "balanced-copa",
+    "e-CARE",
+    "art",
+    "winogrande/winogrande_xl",
+    "codah/codah",
+    "ai2_arc/ARC-Challenge/challenge",
+    "ai2_arc/ARC-Easy/challenge",
+    "definite_pronoun_resolution",
+    "swag/regular",
+    "math_qa",
+    "glue/cola",
+    "glue/sst2",
+    "utilitarianism",
+    "amazon_counterfactual/en",
+    "insincere-questions",
+    "toxic_conversations",
+    "TuringBench",
+    "trec",
+    "vitaminc/tals--vitaminc",
+    "hope_edi/english",
+    "rumoureval_2019/RumourEval2019",
+    "ethos/binary",
+    "ethos/multilabel",
+    "tweet_eval/sentiment",
+    "tweet_eval/offensive",
+    "tweet_eval/emoji",
+    "tweet_eval/emotion",
+    "tweet_eval/irony",
+    "tweet_eval/hate",
+    "tweet_eval/stance_abortion",
+    "tweet_eval/stance_atheism",
+    "tweet_eval/stance_climate",
+    "tweet_eval/stance_feminist",
+    "tweet_eval/stance_hillary",
+    "discovery/discovery",
+    "pragmeval/squinky-informativeness",
+    "pragmeval/switchboard",
+    "pragmeval/mrda",
+    "pragmeval/verifiability",
+    "pragmeval/emobank-arousal",
+    "pragmeval/emobank-dominance",
+    "pragmeval/squinky-formality",
+    "pragmeval/squinky-implicature",
+    "pragmeval/emobank-valence",
+    "pragmeval/persuasiveness-claimtype",
+    "pragmeval/persuasiveness-eloquence",
+    "pragmeval/emergent",
+    "pragmeval/pdtb",
+    "pragmeval/persuasiveness-strength",
+    "pragmeval/persuasiveness-relevance",
+    "pragmeval/persuasiveness-specificity",
+    "pragmeval/persuasiveness-premisetype",
+    "pragmeval/stac",
+    "pragmeval/sarcasm",
+    "pragmeval/gum",
+    "silicone/oasis",
+    "silicone/meld_e",
+    "silicone/meld_s",
+    "silicone/maptask",
+    "silicone/dyda_e",
+    "silicone/dyda_da",
+    "silicone/iemocap",
+    "silicone/sem",
+    "lex_glue/eurlex",
+    "lex_glue/scotus",
+    "lex_glue/ledgar",
+    "lex_glue/unfair_tos",
+    "lex_glue/case_hold",
+    "language-identification",
+    "imdb",
+    "rotten_tomatoes",
+    "ag_news",
+    "yelp_review_full/yelp_review_full",
+    "financial_phrasebank/sentences_allagree",
+    "poem_sentiment",
+    "dbpedia_14/dbpedia_14",
+    "amazon_polarity/amazon_polarity",
+    "app_reviews",
+    "hate_speech18",
+    "sms_spam",
+    "humicroedit/subtask-1",
+    "humicroedit/subtask-2",
+    "snips_built_in_intents",
+    "hate_speech_offensive",
+    "yahoo_answers_topics",
+    "stackoverflow-questions",
+    "hyperpartisan_news",
+    "sciie",
+    "citation_intent",
+    "go_emotions/simplified",
+    "scicite",
+    "liar",
+    "lexical_relation_classification/CogALexV",
+    "lexical_relation_classification/EVALution",
+    "lexical_relation_classification/ROOT09",
+    "lexical_relation_classification/BLESS",
+    "lexical_relation_classification/K&H+N",
+    "linguisticprobing/odd_man_out",
+    "linguisticprobing/tree_depth",
+    "linguisticprobing/coordination_inversion",
+    "linguisticprobing/obj_number",
+    "linguisticprobing/bigram_shift",
+    "linguisticprobing/past_present",
+    "linguisticprobing/sentence_length",
+    "linguisticprobing/top_constituents",
+    "linguisticprobing/subj_number",
+    "crowdflower/political-media-message",
+    "crowdflower/text_emotion",
+    "crowdflower/corporate-messaging",
+    "crowdflower/economic-news",
+    "crowdflower/airline-sentiment",
+    "crowdflower/tweet_global_warming",
+    "crowdflower/sentiment_nuclear_power",
+    "crowdflower/political-media-audience",
+    "crowdflower/political-media-bias",
+    "ethics/commonsense",
+    "ethics/deontology",
+    "ethics/justice",
+    "ethics/virtue",
+    "emo/emo2019",
+    "google_wellformed_query",
+    "tweets_hate_speech_detection",
+    "has_part",
+    "wnut_17/wnut_17",
+    "ncbi_disease/ncbi_disease",
+    "acronym_identification",
+    "jnlpba/jnlpba",
+    "ontonotes_english/SpeedOfMagic--ontonotes_english",
+    "blog_authorship_corpus/gender",
+    "blog_authorship_corpus/age",
+    "blog_authorship_corpus/job",
+    "open_question_type",
+    "health_fact",
+    "commonsense_qa",
+    "mc_taco",
+    "ade_corpus_v2/Ade_corpus_v2_classification",
+    "discosense",
+    "circa",
+    "phrase_similarity",
+    "scientific-exaggeration-detection",
+    "quarel",
+    "fever-evidence-related/mwong--fever-related",
+    "numer_sense",
+    "dynasent/dynabench.dynasent.r1.all/r1",
+    "dynasent/dynabench.dynasent.r2.all/r2",
+    "Sarcasm_News_Headline",
+    "sem_eval_2010_task_8",
+    "auditor_review/demo-org--auditor_review",
+    "medmcqa",
+    "Dynasent_Disagreement",
+    "Politeness_Disagreement",
+    "SBIC_Disagreement",
+    "SChem_Disagreement",
+    "Dilemmas_Disagreement",
+    "logiqa",
+    "wiki_qa",
+    "cycic_classification",
+    "cycic_multiplechoice",
+    "sts-companion",
+    "commonsense_qa_2.0",
+    "lingnli",
+    "monotonicity-entailment",
+    "arct",
+    "scinli",
+    "naturallogic",
+    "onestop_qa",
+    "moral_stories/full",
+    "prost",
+    "dynahate",
+    "syntactic-augmentation-nli",
+    "autotnli",
+    "CONDAQA",
+    "webgpt_comparisons",
+    "synthetic-instruct-gptj-pairwise",
+    "scruples",
+    "wouldyourather",
+    "attempto-nli",
+    "defeasible-nli/atomic",
+    "defeasible-nli/snli",
+    "help-nli",
+    "nli-veridicality-transitivity",
+    "natural-language-satisfiability",
+    "lonli",
+    "dadc-limit-nli",
+    "FLUTE",
+    "strategy-qa",
+    "summarize_from_feedback/comparisons",
+    "folio",
+    "tomi-nli",
+    "avicenna",
+    "SHP",
+    "MedQA-USMLE-4-options-hf",
+    "wikimedqa/medwiki",
+    "cicero",
+    "CREAK",
+    "mutual",
+    "NeQA",
+    "quote-repetition",
+    "redefine-math",
+    "puzzte",
+    "implicatures",
+    "race/middle",
+    "race/high",
+    "race-c",
+    "spartqa-yn",
+    "spartqa-mchoice",
+    "temporal-nli",
+    "riddle_sense",
+    "clcd-english",
+    "twentyquestions",
+    "reclor",
+    "counterfactually-augmented-imdb",
+    "counterfactually-augmented-snli",
+    "cnli",
+    "boolq-natural-perturbations",
+    "acceptability-prediction",
+    "equate",
+    "ScienceQA_text_only",
+    "ekar_english",
+    "implicit-hate-stg1",
+    "chaos-mnli-ambiguity",
+    "headline_cause/en_simple",
+    "logiqa-2.0-nli",
+    "oasst2_dense_flat/quality",
+    "oasst2_dense_flat/toxicity",
+    "oasst2_dense_flat/helpfulness",
+    "mindgames",
+    "universal_dependencies/en_partut/deprel",
+    "universal_dependencies/en_lines/deprel",
+    "universal_dependencies/en_ewt/deprel",
+    "universal_dependencies/en_gum/deprel",
+    "ambient",
+    "path-naturalness-prediction",
+    "civil_comments/toxicity",
+    "civil_comments/severe_toxicity",
+    "civil_comments/obscene",
+    "civil_comments/threat",
+    "civil_comments/insult",
+    "civil_comments/identity_attack",
+    "civil_comments/sexual_explicit",
+    "cloth",
+    "dgen",
+    "I2D2",
+    "args_me",
+    "Touche23-ValueEval",
+    "starcon",
+    "banking77",
+    "lsat_qa/all",
+    "ConTRoL-nli",
+    "tracie",
+    "sherliic",
+    "sen-making/1",
+    "sen-making/2",
+    "winowhy",
+    "mbib-base/cognitive-bias",
+    "mbib-base/fake-news",
+    "mbib-base/gender-bias",
+    "mbib-base/hate-speech",
+    "mbib-base/linguistic-bias",
+    "mbib-base/political-bias",
+    "mbib-base/racial-bias",
+    "mbib-base/text-level-bias",
+    "robustLR",
+    "v1/gen_train234_test2to10",
+    "logical-fallacy",
+    "parade",
+    "cladder",
+    "subjectivity",
+    "MOH",
+    "VUAC",
+    "TroFi",
+    "sharc_modified/mod",
+    "conceptrules_v2",
+    "disrpt/eng.dep.scidtb.rels",
+    "conll2000",
+    "few-nerd/supervised",
+    "finer-139",
+    "zero-shot-label-nli",
+    "com2sense",
+    "scone",
+    "winodict",
+    "fool-me-twice",
+    "monli",
+    "corr2cause",
+    "lsat_qa/all",
+    "apt",
+    "twitter-financial-news-sentiment",
+    "icl-symbol-tuning-instruct",
+    "SpaceNLI",
+    "propsegment/nli",
+    "HatemojiBuild",
+    "regset",
+    "esci",
+    "chatbot_arena_conversations",
+    "dnd_style_intents",
+    "FLD.v2",
+    "SDOH-NLI",
+    "scifact_entailment",
+    "feasibilityQA",
+    "simple_pair",
+    "AdjectiveScaleProbe-nli",
+    "resnli",
+    "SpaRTUN",
+    "ReSQ",
+    "semantic_fragments_nli",
+    "dataset_train_nli",
+    "stepgame",
+    "nlgraph",
+    "oasst2_pairwise_rlhf_reward",
+    "hh-rlhf/helpful-online",
+    "hh-rlhf/helpful-base",
+    "hh-rlhf/helpful-rejection-sampled",
+    "hh-rlhf/harmless-base",
+    "ruletaker",
+    "PARARULE-Plus",
+    "proofwriter",
+    "logical-entailment",
+    "nope",
+    "LogicNLI",
+    "babi_nli",
+    "gen_debiased_nli",
+    "imppres/presupposition",
+    "/prag",
+    "blimp-2",
+    "mmlu-4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

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:acd33a74705e0b74eb83a29a876a5d6b0840eef3a43d9d86b3935d4fba40ef5f
+size 1736094384

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 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "max_length": 256,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}