n_layers_per_step = 1, last_layer_weight = 1.5 * model_layers,, prior_layers_weight= 1, kl_div_weight = 2, kl_temperature= 1,

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,637 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:67190
+- loss:AdaptiveLayerLoss
+- loss:MultipleNegativesRankingLoss
+base_model: microsoft/deberta-v3-small
+datasets:
+- stanfordnlp/snli
+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
+widget:
+- source_sentence: A man is walking past a large sign that says E.S.E. Electronics.
+  sentences:
+  - a child opens a present on his birthday
+  - The man works at E.S.E Electronics.
+  - The soccer team in blue plays soccer.
+- source_sentence: This child is on the library steps.
+  sentences:
+  - A mother dog checking up on her baby puppy.
+  - A guy bites into a freshly opened marshmallow chick
+  - The child is on the steps inside the library.
+- source_sentence: Two men are standing in a boat.
+  sentences:
+  - People are watching the flowers blossom
+  - The couple is married.
+  - A few men are fishing on a boat.
+- source_sentence: Four men playing drums in very orange lighting while one of them
+    is also drinking something out of a bottle.
+  sentences:
+  - four men play drums
+  - The man puts something on the other mans head.
+  - The dogs are in the backyard.
+- source_sentence: First Lady Laura Bush at podium, in front of seated audience, at
+    the White House Conference on Global Literacy.
+  sentences:
+  - Some people are exercising outside.
+  - The former First Lady is at the podium for a conference.
+  - This person is going to the waterfall
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on microsoft/deberta-v3-small
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy
+      value: 0.6605795351645035
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.688193678855896
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.7076101468624832
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.5949093103408813
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.6053997923156802
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.8513434579439252
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.7024412828441404
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.6320555387865983
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 152.9224853515625
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.6979234972677596
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 110.95356750488281
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.5576318546978694
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9325350467289719
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.6470829330129519
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.661334138243284
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 235.78744506835938
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.7093479035514908
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 285.1435852050781
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.5977977977977978
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.8720794392523364
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.7110821827765943
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.6605795351645035
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 12.528359413146973
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.7051541483156768
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 13.97222900390625
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.5951376331123167
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.865070093457944
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.7071775256273181
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.661334138243284
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 235.78744506835938
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.7093479035514908
+      name: Max F1
+    - type: max_f1_threshold
+      value: 285.1435852050781
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.6053997923156802
+      name: Max Precision
+    - type: max_recall
+      value: 0.9325350467289719
+      name: Max Recall
+    - type: max_ap
+      value: 0.7110821827765943
+      name: Max Ap
+---
+
+# SentenceTransformer based on microsoft/deberta-v3-small
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) dataset. It maps sentences & paragraphs to a 768-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:** [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) <!-- at revision a36c739020e01763fe789b4b85e2df55d6180012 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli)
+- **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': 768, '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("bobox/DeBERTaV3-small-ST-AdaptiveLayer-Norm-ep2")
+# Run inference
+sentences = [
+    'First Lady Laura Bush at podium, in front of seated audience, at the White House Conference on Global Literacy.',
+    'The former First Lady is at the podium for a conference.',
+    'This person is going to the waterfall',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# 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
+
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.6606     |
+| cosine_accuracy_threshold    | 0.6882     |
+| cosine_f1                    | 0.7076     |
+| cosine_f1_threshold          | 0.5949     |
+| cosine_precision             | 0.6054     |
+| cosine_recall                | 0.8513     |
+| cosine_ap                    | 0.7024     |
+| dot_accuracy                 | 0.6321     |
+| dot_accuracy_threshold       | 152.9225   |
+| dot_f1                       | 0.6979     |
+| dot_f1_threshold             | 110.9536   |
+| dot_precision                | 0.5576     |
+| dot_recall                   | 0.9325     |
+| dot_ap                       | 0.6471     |
+| manhattan_accuracy           | 0.6613     |
+| manhattan_accuracy_threshold | 235.7874   |
+| manhattan_f1                 | 0.7093     |
+| manhattan_f1_threshold       | 285.1436   |
+| manhattan_precision          | 0.5978     |
+| manhattan_recall             | 0.8721     |
+| manhattan_ap                 | 0.7111     |
+| euclidean_accuracy           | 0.6606     |
+| euclidean_accuracy_threshold | 12.5284    |
+| euclidean_f1                 | 0.7052     |
+| euclidean_f1_threshold       | 13.9722    |
+| euclidean_precision          | 0.5951     |
+| euclidean_recall             | 0.8651     |
+| euclidean_ap                 | 0.7072     |
+| max_accuracy                 | 0.6613     |
+| max_accuracy_threshold       | 235.7874   |
+| max_f1                       | 0.7093     |
+| max_f1_threshold             | 285.1436   |
+| max_precision                | 0.6054     |
+| max_recall                   | 0.9325     |
+| **max_ap**                   | **0.7111** |
+
+<!--
+## 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
+
+#### stanfordnlp/snli
+
+* Dataset: [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) at [cdb5c3d](https://huggingface.co/datasets/stanfordnlp/snli/tree/cdb5c3d5eed6ead6e5a341c8e56e669bb666725b)
+* Size: 67,190 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: 4 tokens</li><li>mean: 21.19 tokens</li><li>max: 133 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 11.77 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>0: 100.00%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                              | sentence2                                                                                        | label          |
+  |:---------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Without a placebo group, we still won't know if any of the treatments are better than nothing and therefore worth giving.</code> | <code>It is necessary to use a controlled method to ensure the treatments are worthwhile.</code> | <code>0</code> |
+  | <code>It was conducted in silence.</code>                                                                                              | <code>It was done silently.</code>                                                               | <code>0</code> |
+  | <code>oh Lewisville  any decent food in your cafeteria up there</code>                                                                 | <code>Is there any decent food in your cafeteria up there in Lewisville?</code>                  | <code>0</code> |
+* Loss: [<code>AdaptiveLayerLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#adaptivelayerloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "n_layers_per_step": 1,
+      "last_layer_weight": 1.5,
+      "prior_layers_weight": 1,
+      "kl_div_weight": 2,
+      "kl_temperature": 1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### stanfordnlp/snli
+
+* Dataset: [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) at [cdb5c3d](https://huggingface.co/datasets/stanfordnlp/snli/tree/cdb5c3d5eed6ead6e5a341c8e56e669bb666725b)
+* Size: 6,626 evaluation samples
+* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | premise                                                                           | hypothesis                                                                        | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 17.28 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.53 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>0: ~48.70%</li><li>1: ~51.30%</li></ul> |
+* Samples:
+  | premise                                                                                                 | hypothesis                                         | label          |
+  |:--------------------------------------------------------------------------------------------------------|:---------------------------------------------------|:---------------|
+  | <code>This church choir sings to the masses as they sing joyous songs from the book at a church.</code> | <code>The church has cracks in the ceiling.</code> | <code>0</code> |
+  | <code>This church choir sings to the masses as they sing joyous songs from the book at a church.</code> | <code>The church is filled with song.</code>       | <code>1</code> |
+  | <code>A woman with a green headscarf, blue shirt and a very big grin.</code>                            | <code>The woman is young.</code>                   | <code>0</code> |
+* Loss: [<code>AdaptiveLayerLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#adaptivelayerloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "n_layers_per_step": 1,
+      "last_layer_weight": 1.5,
+      "prior_layers_weight": 1,
+      "kl_div_weight": 2,
+      "kl_temperature": 1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 45
+- `per_device_eval_batch_size`: 22
+- `learning_rate`: 3e-06
+- `weight_decay`: 1e-09
+- `num_train_epochs`: 2
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.5
+- `save_safetensors`: False
+- `fp16`: True
+- `push_to_hub`: True
+- `hub_model_id`: bobox/DeBERTaV3-small-ST-AdaptiveLayer-Norm-ep2-checkpoints
+- `hub_strategy`: checkpoint
+- `batch_sampler`: no_duplicates
+
+#### 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`: 45
+- `per_device_eval_batch_size`: 22
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `learning_rate`: 3e-06
+- `weight_decay`: 1e-09
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 2
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.5
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: False
+- `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`: True
+- `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`: False
+- `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`: True
+- `resume_from_checkpoint`: None
+- `hub_model_id`: bobox/DeBERTaV3-small-ST-AdaptiveLayer-Norm-ep2-checkpoints
+- `hub_strategy`: checkpoint
+- `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
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | max_ap |
+|:------:|:----:|:-------------:|:------:|:------:|
+| 0.1004 | 150  | 6.8384        | -      | -      |
+| 0.2001 | 299  | -             | 6.3046 | 0.6155 |
+| 0.2008 | 300  | 5.9024        | -      | -      |
+| 0.3012 | 450  | 4.9822        | -      | -      |
+| 0.4003 | 598  | -             | 5.1572 | 0.6595 |
+| 0.4016 | 600  | 4.3996        | -      | -      |
+| 0.5020 | 750  | 3.6015        | -      | -      |
+| 0.6004 | 897  | -             | 4.0073 | 0.6904 |
+| 0.6024 | 900  | 3.0732        | -      | -      |
+| 0.7028 | 1050 | 2.7211        | -      | -      |
+| 0.8005 | 1196 | -             | 3.3433 | 0.7034 |
+| 0.8032 | 1200 | 2.4196        | -      | -      |
+| 0.9036 | 1350 | 2.2256        | -      | -      |
+| 1.0007 | 1495 | -             | 2.9401 | 0.7079 |
+| 1.0040 | 1500 | 2.0015        | -      | -      |
+| 1.1044 | 1650 | 1.9828        | -      | -      |
+| 1.2008 | 1794 | -             | 2.8339 | 0.7104 |
+| 1.2048 | 1800 | 1.8243        | -      | -      |
+| 1.3052 | 1950 | 1.7393        | -      | -      |
+| 1.4009 | 2093 | -             | 2.5906 | 0.7120 |
+| 1.4056 | 2100 | 1.7702        | -      | -      |
+| 1.5060 | 2250 | 1.615         | -      | -      |
+| 1.6011 | 2392 | -             | 2.5455 | 0.7111 |
+| 1.6064 | 2400 | 1.6249        | -      | -      |
+| 1.7068 | 2550 | 1.5804        | -      | -      |
+| 1.8012 | 2691 | -             | 2.4747 | 0.7111 |
+| 1.8072 | 2700 | 1.5935        | -      | -      |
+| 1.9076 | 2850 | 1.5088        | -      | -      |
+
+
+### Framework Versions
+- Python: 3.10.13
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2
+- Accelerate: 0.30.1
+- Datasets: 2.19.2
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```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",
+}
+```
+
+#### AdaptiveLayerLoss
+```bibtex
+@misc{li20242d,
+    title={2D Matryoshka Sentence Embeddings}, 
+    author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li},
+    year={2024},
+    eprint={2402.14776},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2Model"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

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"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b93c9d7c3dd14655bcd8b8f7526e0c331aeb9ead053243ae631a7970785cfee
+size 565251810

sentence_bert_config.json

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

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "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 +1,58 @@
+{
+  "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]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}