Upload folder using huggingface_hub

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 +1,671 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:57306
+- loss:MultipleNegativesRankingLoss
+base_model: allenai/specter2_base
+widget:
+- source_sentence: UCLR RTS timing
+  sentences:
+  - 'Timing without a timer. '
+  - 'Global structural changes in annexin 12. The roles of phospholipid, Ca2+, and
+    pH. '
+  - 'Length of time between surgery and return to sport after ulnar collateral ligament
+    reconstruction in Major League Baseball pitchers does not predict need for revision
+    surgery. '
+- source_sentence: Levofloxacin efficacy in bone and joint infections
+  sentences:
+  - 'Levofloxacin. '
+  - 'Squamous cell carcinoma of the uterine cervix producing granulocyte colony-stimulating
+    factor: a report of 4 cases and a review of the literature. '
+  - 'Levofloxacin at the usual dosage to treat bone and joint infections: a cohort
+    analysis. '
+- source_sentence: Electrical impedance tomography in Barrett's oesophagus
+  sentences:
+  - 'Barrett''s oesophagus: epidemiology, diagnosis and clinical management. '
+  - 'Assessing the conditions for in vivo electrical virtual biopsies in Barrett''s
+    oesophagus. '
+  - 'Serum aminoterminal propeptide of type III procollagen: a potential predictor
+    of the response to growth hormone therapy. '
+- source_sentence: Population Aging Theory
+  sentences:
+  - 'A cybernetic theory of aging. '
+  - '[In process]. '
+  - 'Robine and Michel''s "Looking forward to a general theory on population aging":
+    commentary. '
+- source_sentence: Algesimetric study of hypoalgesic effect
+  sentences:
+  - 'Regulation of ATG4B stability by RNF5 limits basal levels of autophagy and influences
+    susceptibility to bacterial infection. '
+  - '[Pain analysis is basis for correct choice of therapeutic method]. '
+  - '[Experimental algesimetric study of the hypoalgesic effect of body acupuncture]. '
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on allenai/specter2_base
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: NanoNQ
+      type: NanoNQ
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.02
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.06
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.08
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.22
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.02
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.02
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.016
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.022000000000000002
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.01
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.05
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.07
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.19
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.08358031930860417
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.060047619047619044
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.05702682179889267
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: NanoMSMARCO
+      type: NanoMSMARCO
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.12
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.3
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.34
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.44
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.12
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.1
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.068
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.044000000000000004
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.12
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.3
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.34
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.44
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2718119392465092
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.21891269841269842
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.22988006901512154
+      name: Cosine Map@100
+  - task:
+      type: nano-beir
+      name: Nano BEIR
+    dataset:
+      name: NanoBEIR mean
+      type: NanoBEIR_mean
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.06999999999999999
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.18
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.21000000000000002
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.33
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.06999999999999999
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.060000000000000005
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.042
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.033
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.065
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.175
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.20500000000000002
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.315
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.17769612927755668
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.13948015873015873
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.1434534454070071
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on allenai/specter2_base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [allenai/specter2_base](https://huggingface.co/allenai/specter2_base) on the json 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:** [allenai/specter2_base](https://huggingface.co/allenai/specter2_base) <!-- at revision 3447645e1def9117997203454fa4495937bfbd83 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+<!-- - **Language:** Unknown -->
+<!-- - **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: BertModel 
+  (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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Algesimetric study of hypoalgesic effect',
+    '[Experimental algesimetric study of the hypoalgesic effect of body acupuncture]. ',
+    '[Pain analysis is basis for correct choice of therapeutic method]. ',
+]
+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
+
+#### Information Retrieval
+
+* Datasets: `NanoNQ` and `NanoMSMARCO`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | NanoNQ     | NanoMSMARCO |
+|:--------------------|:-----------|:------------|
+| cosine_accuracy@1   | 0.02       | 0.12        |
+| cosine_accuracy@3   | 0.06       | 0.3         |
+| cosine_accuracy@5   | 0.08       | 0.34        |
+| cosine_accuracy@10  | 0.22       | 0.44        |
+| cosine_precision@1  | 0.02       | 0.12        |
+| cosine_precision@3  | 0.02       | 0.1         |
+| cosine_precision@5  | 0.016      | 0.068       |
+| cosine_precision@10 | 0.022      | 0.044       |
+| cosine_recall@1     | 0.01       | 0.12        |
+| cosine_recall@3     | 0.05       | 0.3         |
+| cosine_recall@5     | 0.07       | 0.34        |
+| cosine_recall@10    | 0.19       | 0.44        |
+| **cosine_ndcg@10**  | **0.0836** | **0.2718**  |
+| cosine_mrr@10       | 0.06       | 0.2189      |
+| cosine_map@100      | 0.057      | 0.2299      |
+
+#### Nano BEIR
+
+* Dataset: `NanoBEIR_mean`
+* Evaluated with [<code>NanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.NanoBEIREvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.07       |
+| cosine_accuracy@3   | 0.18       |
+| cosine_accuracy@5   | 0.21       |
+| cosine_accuracy@10  | 0.33       |
+| cosine_precision@1  | 0.07       |
+| cosine_precision@3  | 0.06       |
+| cosine_precision@5  | 0.042      |
+| cosine_precision@10 | 0.033      |
+| cosine_recall@1     | 0.065      |
+| cosine_recall@3     | 0.175      |
+| cosine_recall@5     | 0.205      |
+| cosine_recall@10    | 0.315      |
+| **cosine_ndcg@10**  | **0.1777** |
+| cosine_mrr@10       | 0.1395     |
+| cosine_map@100      | 0.1435     |
+
+<!--
+## 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
+
+#### json
+
+* Dataset: json
+* Size: 57,306 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: 4 tokens</li><li>mean: 7.57 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 20.36 tokens</li><li>max: 78 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 12.38 tokens</li><li>max: 49 tokens</li></ul> |
+* Samples:
+  | anchor                                               | positive                                                                                                                                                             | negative                                                                             |
+  |:-----------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | <code>Intramedullary Hemangioblastoma</code>         | <code>Hydrocephalus: a rare initial manifestation of sporadic intramedullary hemangioblastoma : Intramedullary hemangioblastoma presenting as hydrocephalus. </code> | <code>Intramedullary capillary haemangioma. </code>                                  |
+  | <code>Density-based load estimation algorithm</code> | <code>A contact algorithm for density-based load estimation. </code>                                                                                                 | <code>Density propagation based adaptive multi-density clustering algorithm. </code> |
+  | <code>Herbicide Adjuvant Efficacy</code>             | <code>The efficiency of adjuvants combined with flupyrsulfuron-methyl plus metsulfuron-methyl (Lexus XPE) on weed control. </code>                                   | <code>Are herbicides a once in a century method of weed control? </code>             |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 2e-07
+- `num_train_epochs`: 1
+- `lr_scheduler_type`: cosine_with_restarts
+- `warmup_ratio`: 0.1
+- `bf16`: 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`: True
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 4
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-07
+- `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`: cosine_with_restarts
+- `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`: True
+- `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`: 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`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `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
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | NanoNQ_cosine_ndcg@10 | NanoMSMARCO_cosine_ndcg@10 | NanoBEIR_mean_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------------:|:--------------------------:|:----------------------------:|
+| 0      | 0    | -             | 0.0682                | 0.2560                     | 0.1621                       |
+| 0.0134 | 1    | 14.8664       | -                     | -                          | -                            |
+| 0.0268 | 2    | 14.6017       | -                     | -                          | -                            |
+| 0.0401 | 3    | 14.8474       | -                     | -                          | -                            |
+| 0.0535 | 4    | 14.7156       | -                     | -                          | -                            |
+| 0.0669 | 5    | 14.5967       | -                     | -                          | -                            |
+| 0.0803 | 6    | 14.8373       | -                     | -                          | -                            |
+| 0.0936 | 7    | 14.7819       | -                     | -                          | -                            |
+| 0.1070 | 8    | 14.5891       | -                     | -                          | -                            |
+| 0.1204 | 9    | 14.5531       | -                     | -                          | -                            |
+| 0.1338 | 10   | 14.5441       | -                     | -                          | -                            |
+| 0.1472 | 11   | 14.5516       | -                     | -                          | -                            |
+| 0.1605 | 12   | 14.5739       | -                     | -                          | -                            |
+| 0.1739 | 13   | 14.5974       | -                     | -                          | -                            |
+| 0.1873 | 14   | 14.4102       | -                     | -                          | -                            |
+| 0.2007 | 15   | 14.3615       | -                     | -                          | -                            |
+| 0.2140 | 16   | 14.2877       | -                     | -                          | -                            |
+| 0.2274 | 17   | 14.2774       | -                     | -                          | -                            |
+| 0.2408 | 18   | 14.4985       | -                     | -                          | -                            |
+| 0.2542 | 19   | 14.2307       | -                     | -                          | -                            |
+| 0.2676 | 20   | 14.3657       | -                     | -                          | -                            |
+| 0.2809 | 21   | 14.3261       | -                     | -                          | -                            |
+| 0.2943 | 22   | 14.2946       | -                     | -                          | -                            |
+| 0.3077 | 23   | 14.2311       | -                     | -                          | -                            |
+| 0.3211 | 24   | 14.0789       | -                     | -                          | -                            |
+| 0.3344 | 25   | 13.9392       | 0.0764                | 0.2652                     | 0.1708                       |
+| 0.3478 | 26   | 14.0972       | -                     | -                          | -                            |
+| 0.3612 | 27   | 14.0966       | -                     | -                          | -                            |
+| 0.3746 | 28   | 13.9205       | -                     | -                          | -                            |
+| 0.3880 | 29   | 13.8919       | -                     | -                          | -                            |
+| 0.4013 | 30   | 14.1233       | -                     | -                          | -                            |
+| 0.4147 | 31   | 14.1351       | -                     | -                          | -                            |
+| 0.4281 | 32   | 14.1106       | -                     | -                          | -                            |
+| 0.4415 | 33   | 14.166        | -                     | -                          | -                            |
+| 0.4548 | 34   | 13.7817       | -                     | -                          | -                            |
+| 0.4682 | 35   | 14.0178       | -                     | -                          | -                            |
+| 0.4816 | 36   | 13.8457       | -                     | -                          | -                            |
+| 0.4950 | 37   | 14.074        | -                     | -                          | -                            |
+| 0.5084 | 38   | 13.9665       | -                     | -                          | -                            |
+| 0.5217 | 39   | 13.9726       | -                     | -                          | -                            |
+| 0.5351 | 40   | 13.8546       | -                     | -                          | -                            |
+| 0.5485 | 41   | 13.9037       | -                     | -                          | -                            |
+| 0.5619 | 42   | 13.6977       | -                     | -                          | -                            |
+| 0.5753 | 43   | 14.0445       | -                     | -                          | -                            |
+| 0.5886 | 44   | 13.93         | -                     | -                          | -                            |
+| 0.6020 | 45   | 13.7835       | -                     | -                          | -                            |
+| 0.6154 | 46   | 13.819        | -                     | -                          | -                            |
+| 0.6288 | 47   | 13.6248       | -                     | -                          | -                            |
+| 0.6421 | 48   | 13.846        | -                     | -                          | -                            |
+| 0.6555 | 49   | 13.6079       | -                     | -                          | -                            |
+| 0.6689 | 50   | 13.6848       | 0.0836                | 0.2724                     | 0.1780                       |
+| 0.6823 | 51   | 13.668        | -                     | -                          | -                            |
+| 0.6957 | 52   | 13.5784       | -                     | -                          | -                            |
+| 0.7090 | 53   | 13.7519       | -                     | -                          | -                            |
+| 0.7224 | 54   | 13.6455       | -                     | -                          | -                            |
+| 0.7358 | 55   | 13.6757       | -                     | -                          | -                            |
+| 0.7492 | 56   | 13.5647       | -                     | -                          | -                            |
+| 0.7625 | 57   | 13.7072       | -                     | -                          | -                            |
+| 0.7759 | 58   | 13.5603       | -                     | -                          | -                            |
+| 0.7893 | 59   | 13.6437       | -                     | -                          | -                            |
+| 0.8027 | 60   | 13.6656       | -                     | -                          | -                            |
+| 0.8161 | 61   | 13.479        | -                     | -                          | -                            |
+| 0.8294 | 62   | 13.5965       | -                     | -                          | -                            |
+| 0.8428 | 63   | 13.6793       | -                     | -                          | -                            |
+| 0.8562 | 64   | 13.6121       | -                     | -                          | -                            |
+| 0.8696 | 65   | 13.841        | -                     | -                          | -                            |
+| 0.8829 | 66   | 13.4793       | -                     | -                          | -                            |
+| 0.8963 | 67   | 13.5875       | -                     | -                          | -                            |
+| 0.9097 | 68   | 13.4063       | -                     | -                          | -                            |
+| 0.9231 | 69   | 13.6365       | -                     | -                          | -                            |
+| 0.9365 | 70   | 13.4696       | -                     | -                          | -                            |
+| 0.9498 | 71   | 13.5018       | -                     | -                          | -                            |
+| 0.9632 | 72   | 13.5956       | -                     | -                          | -                            |
+| 0.9766 | 73   | 13.3945       | -                     | -                          | -                            |
+| 0.9900 | 74   | 13.5684       | 0.0836                | 0.2718                     | 0.1777                       |
+
+
+### Framework Versions
+- Python: 3.12.3
+- Sentence Transformers: 3.3.1
+- Transformers: 4.49.0
+- PyTorch: 2.5.1
+- Accelerate: 1.2.1
+- Datasets: 2.19.0
+- Tokenizers: 0.21.0
+
+## 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",
+}
+```
+
+#### 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 +1,31 @@
+{
+  "_name_or_path": "allenai/specter2_base",
+  "adapters": {
+    "adapters": {},
+    "config_map": {},
+    "fusion_config_map": {},
+    "fusions": {}
+  },
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.49.0",
+    "pytorch": "2.5.1"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8bcd96b6b1acacc0a66486e23abd76008ca6c512202c3a457a7f9d12fab36a6
+size 439696224

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 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}