Add new SentenceTransformer model.

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 +1,632 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- loss:Matryoshka2dLoss
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: distilbert/distilroberta-base
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: A woman is reading.
+  sentences:
+  - A woman is writing something.
+  - A man helps a boy ride a bike.
+  - A group wading across a ditch
+- source_sentence: A man shoots a man.
+  sentences:
+  - A man with a pistol shoots another man.
+  - Suicide bomber strikes in Syria
+  - China and Taiwan hold historic talks
+- source_sentence: A boy is vacuuming.
+  sentences:
+  - A little boy is vacuuming the floor.
+  - 'Breivik: Jail term ''ridiculous'''
+  - Glorious triple-gold night for Britain
+- source_sentence: A man is spitting.
+  sentences:
+  - A man is speaking.
+  - The boy is jumping into a lake.
+  - 10 Things to Know for Thursday
+- source_sentence: A plane in the sky.
+  sentences:
+  - Two airplanes in the sky.
+  - Nelson Mandela undergoes surgery
+  - Nelson Mandela undergoes surgery
+pipeline_tag: sentence-similarity
+co2_eq_emissions:
+  emissions: 69.2573690422145
+  energy_consumed: 0.1781760038338226
+  source: codecarbon
+  training_type: fine-tuning
+  on_cloud: false
+  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
+  ram_total_size: 31.777088165283203
+  hours_used: 0.626
+  hardware_used: 1 x NVIDIA GeForce RTX 3090
+model-index:
+- name: SentenceTransformer based on distilbert/distilroberta-base
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.8395203447657347
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8424556124488326
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8432537220190851
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8435994230515586
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8440900768179745
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8449067313707376
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.763767029856877
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7569706383510251
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8440900768179745
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8449067313707376
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.8186702838538092
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8170686920551
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8117192659894803
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.804879002947593
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8127154744140831
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8058410028545979
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7396245702595934
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7256120569318246
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8186702838538092
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8170686920551
+      name: Spearman Max
+---
+
+# SentenceTransformer based on distilbert/distilroberta-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) 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:** [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) <!-- at revision fb53ab8802853c8e4fbdbcd0529f21fc6f459b2b -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
+- **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: RobertaModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, '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("tomaarsen/distilroberta-base-nli-2d-matryoshka")
+# Run inference
+sentences = [
+    'A plane in the sky.',
+    'Two airplanes in the sky.',
+    'Nelson Mandela undergoes surgery',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(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
+
+#### Semantic Similarity
+* Dataset: `sts-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8395     |
+| **spearman_cosine** | **0.8425** |
+| pearson_manhattan   | 0.8433     |
+| spearman_manhattan  | 0.8436     |
+| pearson_euclidean   | 0.8441     |
+| spearman_euclidean  | 0.8449     |
+| pearson_dot         | 0.7638     |
+| spearman_dot        | 0.757      |
+| pearson_max         | 0.8441     |
+| spearman_max        | 0.8449     |
+
+#### Semantic Similarity
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8187     |
+| **spearman_cosine** | **0.8171** |
+| pearson_manhattan   | 0.8117     |
+| spearman_manhattan  | 0.8049     |
+| pearson_euclidean   | 0.8127     |
+| spearman_euclidean  | 0.8058     |
+| pearson_dot         | 0.7396     |
+| spearman_dot        | 0.7256     |
+| pearson_max         | 0.8187     |
+| spearman_max        | 0.8171     |
+
+<!--
+## 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
+
+#### sentence-transformers/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [65dd388](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/65dd38867b600f42241d2066ba1a35fbd097fcfe)
+* Size: 557,850 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                         | negative                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 10.38 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.8 tokens</li><li>max: 39 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.4 tokens</li><li>max: 50 tokens</li></ul> |
+* Samples:
+  | anchor                                                                     | positive                                         | negative                                                   |
+  |:---------------------------------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------------|
+  | <code>A person on a horse jumps over a broken down airplane.</code>        | <code>A person is outdoors, on a horse.</code>   | <code>A person is at a diner, ordering an omelette.</code> |
+  | <code>Children smiling and waving at camera</code>                         | <code>There are children present</code>          | <code>The kids are frowning</code>                         |
+  | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>The boy skates down the sidewalk.</code>             |
+* Loss: [<code>Matryoshka2dLoss</code>](https://sbert.net/docs/package_reference/losses.html#matryoshka2dloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "n_layers_per_step": 1,
+      "last_layer_weight": 1.0,
+      "prior_layers_weight": 1.0,
+      "kl_div_weight": 1.0,
+      "kl_temperature": 0.3,
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": 1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### sentence-transformers/stsb
+
+* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                         | score                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | float                                                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 15.0 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.99 tokens</li><li>max: 61 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.47</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                         | sentence2                                             | score             |
+  |:--------------------------------------------------|:------------------------------------------------------|:------------------|
+  | <code>A man with a hard hat is dancing.</code>    | <code>A man wearing a hard hat is dancing.</code>     | <code>1.0</code>  |
+  | <code>A young child is riding a horse.</code>     | <code>A child is riding a horse.</code>               | <code>0.95</code> |
+  | <code>A man is feeding a mouse to a snake.</code> | <code>The man is feeding a mouse to the snake.</code> | <code>1.0</code>  |
+* Loss: [<code>Matryoshka2dLoss</code>](https://sbert.net/docs/package_reference/losses.html#matryoshka2dloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "n_layers_per_step": 1,
+      "last_layer_weight": 1.0,
+      "prior_layers_weight": 1.0,
+      "kl_div_weight": 1.0,
+      "kl_temperature": 0.3,
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": 1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `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`: False
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `learning_rate`: 5e-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`: 1
+- `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
+- `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`: None
+- `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_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | sts-dev_spearman_cosine | sts-test_spearman_cosine |
+|:------:|:----:|:-------------:|:------:|:-----------------------:|:------------------------:|
+| 0.0229 | 100  | 6.2779        | 3.9959 | 0.8008                  | -                        |
+| 0.0459 | 200  | 4.3212        | 3.5818 | 0.7956                  | -                        |
+| 0.0688 | 300  | 3.7135        | 3.4422 | 0.7940                  | -                        |
+| 0.0918 | 400  | 3.5567        | 3.5458 | 0.7951                  | -                        |
+| 0.1147 | 500  | 3.1297        | 3.1253 | 0.8050                  | -                        |
+| 0.1376 | 600  | 2.7001        | 3.4366 | 0.7996                  | -                        |
+| 0.1606 | 700  | 2.8664        | 3.6609 | 0.8033                  | -                        |
+| 0.1835 | 800  | 2.6656        | 3.3736 | 0.7975                  | -                        |
+| 0.2065 | 900  | 2.633         | 3.3735 | 0.8076                  | -                        |
+| 0.2294 | 1000 | 2.4335        | 3.6499 | 0.7996                  | -                        |
+| 0.2524 | 1100 | 2.4165        | 3.6301 | 0.8015                  | -                        |
+| 0.2753 | 1200 | 2.2942        | 3.1541 | 0.7994                  | -                        |
+| 0.2982 | 1300 | 2.2402        | 3.4284 | 0.7977                  | -                        |
+| 0.3212 | 1400 | 2.2148        | 3.3775 | 0.7988                  | -                        |
+| 0.3441 | 1500 | 2.2285        | 3.6097 | 0.8016                  | -                        |
+| 0.3671 | 1600 | 2.0591        | 3.3839 | 0.7926                  | -                        |
+| 0.3900 | 1700 | 2.0253        | 3.1113 | 0.7981                  | -                        |
+| 0.4129 | 1800 | 2.0244        | 3.8289 | 0.7954                  | -                        |
+| 0.4359 | 1900 | 1.8582        | 3.3515 | 0.8000                  | -                        |
+| 0.4588 | 2000 | 1.977         | 3.3054 | 0.7917                  | -                        |
+| 0.4818 | 2100 | 1.9028        | 3.2166 | 0.7927                  | -                        |
+| 0.5047 | 2200 | 1.8316        | 3.6504 | 0.7955                  | -                        |
+| 0.5276 | 2300 | 1.8404        | 3.2822 | 0.7843                  | -                        |
+| 0.5506 | 2400 | 1.8455        | 3.2583 | 0.7941                  | -                        |
+| 0.5735 | 2500 | 1.9488        | 3.3970 | 0.7971                  | -                        |
+| 0.5965 | 2600 | 1.9403        | 2.8948 | 0.7959                  | -                        |
+| 0.6194 | 2700 | 1.8884        | 3.2227 | 0.8008                  | -                        |
+| 0.6423 | 2800 | 1.8655        | 3.1948 | 0.7920                  | -                        |
+| 0.6653 | 2900 | 1.8567        | 3.4374 | 0.7913                  | -                        |
+| 0.6882 | 3000 | 1.8423        | 3.1118 | 0.7949                  | -                        |
+| 0.7112 | 3100 | 1.7475        | 3.1359 | 0.8062                  | -                        |
+| 0.7341 | 3200 | 1.8166        | 2.9927 | 0.7984                  | -                        |
+| 0.7571 | 3300 | 1.5626        | 3.5143 | 0.8405                  | -                        |
+| 0.7800 | 3400 | 1.2038        | 3.3909 | 0.8411                  | -                        |
+| 0.8029 | 3500 | 1.1579        | 3.2458 | 0.8413                  | -                        |
+| 0.8259 | 3600 | 1.0978        | 3.1592 | 0.8404                  | -                        |
+| 0.8488 | 3700 | 1.0283        | 2.9557 | 0.8408                  | -                        |
+| 0.8718 | 3800 | 0.9993        | 3.4073 | 0.8430                  | -                        |
+| 0.8947 | 3900 | 0.9727        | 3.0570 | 0.8434                  | -                        |
+| 0.9176 | 4000 | 0.9692        | 2.9357 | 0.8439                  | -                        |
+| 0.9406 | 4100 | 0.9412        | 2.9494 | 0.8428                  | -                        |
+| 0.9635 | 4200 | 1.0063        | 3.4047 | 0.8422                  | -                        |
+| 0.9865 | 4300 | 0.9678        | 3.4299 | 0.8425                  | -                        |
+| 1.0    | 4359 | -             | -      | -                       | 0.8171                   |
+
+
+### Environmental Impact
+Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
+- **Energy Consumed**: 0.178 kWh
+- **Carbon Emitted**: 0.069 kg of CO2
+- **Hours Used**: 0.626 hours
+
+### Training Hardware
+- **On Cloud**: No
+- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
+- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
+- **RAM Size**: 31.78 GB
+
+### Framework Versions
+- Python: 3.11.6
+- Sentence Transformers: 3.0.0.dev0
+- Transformers: 4.41.0.dev0
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.26.1
+- Datasets: 2.18.0
+- 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",
+}
+```
+
+#### Matryoshka2dLoss
+```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}
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### 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.*
+-->

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0.dev0",
+    "transformers": "4.41.0.dev0",
+    "pytorch": "2.3.0+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 sha256:026cf20a013db893d3e033405596fd55842b46bd57cb057c0317d713299c7d45
+size 328485128

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 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}