Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "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 +1,644 @@
+---
+base_model: BAAI/bge-small-en-v1.5
+datasets: []
+language: []
+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
+- dot_accuracy@1
+- dot_accuracy@3
+- dot_accuracy@5
+- dot_accuracy@10
+- dot_precision@1
+- dot_precision@3
+- dot_precision@5
+- dot_precision@10
+- dot_recall@1
+- dot_recall@3
+- dot_recall@5
+- dot_recall@10
+- dot_ndcg@10
+- dot_mrr@10
+- dot_map@100
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:491
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: do I have money I vested through [TICKER]
+  sentences:
+  - '[{"get_portfolio([''brokerName''])": "portfolio"}, {"filter(''portfolio'',''brokerName'',''=='',''Magnifi'')":
+    "portfolio"}]'
+  - '[{"get_attribute([''<TICKER1>''],[''returns''],''<DATES>'')": "price_<TICKER1>"}]'
+  - '[{"get_earnings_announcements([''<TICKER1>''],''<DATES>'')": "<TICKER1>_earnings"}]'
+- source_sentence: Knock Knock!
+  sentences:
+  - '[{"get_portfolio([''weight''])": "portfolio"}, {"factor_contribution(''portfolio'',''<DATES>'',''sector'',''sector
+    retailing'',''portfolio'')": "portfolio"}]'
+  - '[{"get_news_articles([''<TICKER1>''],None,None,None)": "news_data_<TICKER1>"}]'
+  - '[]'
+- source_sentence: what's the earnings per share of [TICKER]
+  sentences:
+  - '[{"get_attribute([''<TICKER1>''],[''returns''],''<DATES>'')": "performance_data_<TICKER1>"}]'
+  - '[{"get_attribute([''<TICKER1>''],[''earnings per share''],''<DATES>'')": "earnings_per_share_<TICKER1>"}]'
+  - '[{"get_portfolio([''weight''])": "portfolio"}, {"factor_contribution(''portfolio'',''<DATES>'',''factor'',''momentum'',''portfolio'')":
+    "portfolio"}]'
+- source_sentence: returns of [TICKER] since 2017
+  sentences:
+  - '[{"get_portfolio([''weight''])": "portfolio"}, {"factor_contribution(''portfolio'',''<DATES>'',''factor'',''volatility'',''returns'')":
+    "portfolio"}]'
+  - '[{"get_attribute([''<TICKER1>''],[''returns''],''<DATES>'')": "performance_data_<TICKER1>"}]'
+  - '[{"get_dictionary_definition([''limit order'', ''market order''])": "definitions"}]'
+- source_sentence: how should I play [TICKER] futures contracts
+  sentences:
+  - '[]'
+  - '[{"get_attribute([''<TICKER1>''],[''returns''],''<DATES>'')": "live_price_<TICKER1>"}]'
+  - '[{"get_news_articles(None,None,None,None)": "latest_news_data"}]'
+model-index:
+- name: SentenceTransformer based on BAAI/bge-small-en-v1.5
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7191780821917808
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9246575342465754
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.952054794520548
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9794520547945206
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7191780821917808
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3082191780821918
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19041095890410956
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09794520547945204
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.019977168949771692
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.02568493150684932
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.02644596651445967
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.02720700152207002
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.1886992031917713
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8171314416177428
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.02272901264767703
+      name: Cosine Map@100
+    - type: dot_accuracy@1
+      value: 0.7191780821917808
+      name: Dot Accuracy@1
+    - type: dot_accuracy@3
+      value: 0.9246575342465754
+      name: Dot Accuracy@3
+    - type: dot_accuracy@5
+      value: 0.952054794520548
+      name: Dot Accuracy@5
+    - type: dot_accuracy@10
+      value: 0.9794520547945206
+      name: Dot Accuracy@10
+    - type: dot_precision@1
+      value: 0.7191780821917808
+      name: Dot Precision@1
+    - type: dot_precision@3
+      value: 0.3082191780821918
+      name: Dot Precision@3
+    - type: dot_precision@5
+      value: 0.19041095890410956
+      name: Dot Precision@5
+    - type: dot_precision@10
+      value: 0.09794520547945204
+      name: Dot Precision@10
+    - type: dot_recall@1
+      value: 0.019977168949771692
+      name: Dot Recall@1
+    - type: dot_recall@3
+      value: 0.02568493150684932
+      name: Dot Recall@3
+    - type: dot_recall@5
+      value: 0.02644596651445967
+      name: Dot Recall@5
+    - type: dot_recall@10
+      value: 0.02720700152207002
+      name: Dot Recall@10
+    - type: dot_ndcg@10
+      value: 0.1886992031917713
+      name: Dot Ndcg@10
+    - type: dot_mrr@10
+      value: 0.8171314416177428
+      name: Dot Mrr@10
+    - type: dot_map@100
+      value: 0.02272901264767703
+      name: Dot Map@100
+---
+
+# SentenceTransformer based on BAAI/bge-small-en-v1.5
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5). It maps sentences & paragraphs to a 384-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:** [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) <!-- at revision 5c38ec7c405ec4b44b94cc5a9bb96e735b38267a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **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': True}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## 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 = [
+    'how should I play [TICKER] futures contracts',
+    '[]',
+    '[{"get_attribute([\'<TICKER1>\'],[\'returns\'],\'<DATES>\')": "live_price_<TICKER1>"}]',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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
+
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7192     |
+| cosine_accuracy@3   | 0.9247     |
+| cosine_accuracy@5   | 0.9521     |
+| cosine_accuracy@10  | 0.9795     |
+| cosine_precision@1  | 0.7192     |
+| cosine_precision@3  | 0.3082     |
+| cosine_precision@5  | 0.1904     |
+| cosine_precision@10 | 0.0979     |
+| cosine_recall@1     | 0.02       |
+| cosine_recall@3     | 0.0257     |
+| cosine_recall@5     | 0.0264     |
+| cosine_recall@10    | 0.0272     |
+| cosine_ndcg@10      | 0.1887     |
+| cosine_mrr@10       | 0.8171     |
+| **cosine_map@100**  | **0.0227** |
+| dot_accuracy@1      | 0.7192     |
+| dot_accuracy@3      | 0.9247     |
+| dot_accuracy@5      | 0.9521     |
+| dot_accuracy@10     | 0.9795     |
+| dot_precision@1     | 0.7192     |
+| dot_precision@3     | 0.3082     |
+| dot_precision@5     | 0.1904     |
+| dot_precision@10    | 0.0979     |
+| dot_recall@1        | 0.02       |
+| dot_recall@3        | 0.0257     |
+| dot_recall@5        | 0.0264     |
+| dot_recall@10       | 0.0272     |
+| dot_ndcg@10         | 0.1887     |
+| dot_mrr@10          | 0.8171     |
+| dot_map@100         | 0.0227     |
+
+<!--
+## 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
+
+#### Unnamed Dataset
+
+
+* Size: 491 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                       | sentence_1                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 11.9 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 67.55 tokens</li><li>max: 194 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                  | sentence_1                                                                                                       |
+  |:------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------|
+  | <code>Profitability of [TICKER]</code>                      | <code>[{"get_attribute(['<TICKER1>'],['cash flow profitability'],'<DATES>')": "profitability_<TICKER1>"}]</code> |
+  | <code>[TICKER] momentum</code>                              | <code>[{"get_attribute(['<TICKER1>'],['momentum'],'<DATES>')": "momentum_<TICKER1>"}]</code>                     |
+  | <code>what was the total return of [TICKER] for 2023</code> | <code>[{"get_attribute(['<TICKER1>'],['returns'],'<DATES>')": "performance_data_<TICKER1>"}]</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`: 10
+- `per_device_eval_batch_size`: 10
+- `num_train_epochs`: 6
+- `multi_dataset_batch_sampler`: round_robin
+
+#### 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`: 10
+- `per_device_eval_batch_size`: 10
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_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
+- `num_train_epochs`: 6
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `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`: 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`: 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
+- `eval_use_gather_object`: False
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step | cosine_map@100 |
+|:------:|:----:|:--------------:|
+| 0.04   | 2    | 0.0137         |
+| 0.08   | 4    | 0.0137         |
+| 0.12   | 6    | 0.0138         |
+| 0.16   | 8    | 0.0142         |
+| 0.2    | 10   | 0.0144         |
+| 0.24   | 12   | 0.0147         |
+| 0.28   | 14   | 0.0149         |
+| 0.32   | 16   | 0.0151         |
+| 0.36   | 18   | 0.0155         |
+| 0.4    | 20   | 0.0166         |
+| 0.44   | 22   | 0.0170         |
+| 0.48   | 24   | 0.0174         |
+| 0.52   | 26   | 0.0179         |
+| 0.56   | 28   | 0.0181         |
+| 0.6    | 30   | 0.0184         |
+| 0.64   | 32   | 0.0186         |
+| 0.68   | 34   | 0.0189         |
+| 0.72   | 36   | 0.0191         |
+| 0.76   | 38   | 0.0192         |
+| 0.8    | 40   | 0.0195         |
+| 0.84   | 42   | 0.0195         |
+| 0.88   | 44   | 0.0195         |
+| 0.92   | 46   | 0.0195         |
+| 0.96   | 48   | 0.0196         |
+| 1.0    | 50   | 0.0197         |
+| 1.04   | 52   | 0.0196         |
+| 1.08   | 54   | 0.0198         |
+| 1.12   | 56   | 0.0200         |
+| 1.16   | 58   | 0.0202         |
+| 1.2    | 60   | 0.0202         |
+| 1.24   | 62   | 0.0205         |
+| 1.28   | 64   | 0.0206         |
+| 1.32   | 66   | 0.0207         |
+| 1.3600 | 68   | 0.0208         |
+| 1.4    | 70   | 0.0208         |
+| 1.44   | 72   | 0.0209         |
+| 1.48   | 74   | 0.0210         |
+| 1.52   | 76   | 0.0211         |
+| 1.56   | 78   | 0.0211         |
+| 1.6    | 80   | 0.0209         |
+| 1.6400 | 82   | 0.0210         |
+| 1.6800 | 84   | 0.0209         |
+| 1.72   | 86   | 0.0209         |
+| 1.76   | 88   | 0.0210         |
+| 1.8    | 90   | 0.0211         |
+| 1.8400 | 92   | 0.0211         |
+| 1.88   | 94   | 0.0211         |
+| 1.92   | 96   | 0.0214         |
+| 1.96   | 98   | 0.0216         |
+| 2.0    | 100  | 0.0218         |
+| 2.04   | 102  | 0.0217         |
+| 2.08   | 104  | 0.0217         |
+| 2.12   | 106  | 0.0219         |
+| 2.16   | 108  | 0.0221         |
+| 2.2    | 110  | 0.0219         |
+| 2.24   | 112  | 0.0217         |
+| 2.2800 | 114  | 0.0217         |
+| 2.32   | 116  | 0.0217         |
+| 2.36   | 118  | 0.0218         |
+| 2.4    | 120  | 0.0219         |
+| 2.44   | 122  | 0.0219         |
+| 2.48   | 124  | 0.0219         |
+| 2.52   | 126  | 0.0222         |
+| 2.56   | 128  | 0.0220         |
+| 2.6    | 130  | 0.0221         |
+| 2.64   | 132  | 0.0221         |
+| 2.68   | 134  | 0.0221         |
+| 2.7200 | 136  | 0.0221         |
+| 2.76   | 138  | 0.0222         |
+| 2.8    | 140  | 0.0222         |
+| 2.84   | 142  | 0.0224         |
+| 2.88   | 144  | 0.0224         |
+| 2.92   | 146  | 0.0223         |
+| 2.96   | 148  | 0.0224         |
+| 3.0    | 150  | 0.0223         |
+| 3.04   | 152  | 0.0223         |
+| 3.08   | 154  | 0.0223         |
+| 3.12   | 156  | 0.0223         |
+| 3.16   | 158  | 0.0223         |
+| 3.2    | 160  | 0.0223         |
+| 3.24   | 162  | 0.0223         |
+| 3.2800 | 164  | 0.0223         |
+| 3.32   | 166  | 0.0223         |
+| 3.36   | 168  | 0.0223         |
+| 3.4    | 170  | 0.0223         |
+| 3.44   | 172  | 0.0224         |
+| 3.48   | 174  | 0.0224         |
+| 3.52   | 176  | 0.0225         |
+| 3.56   | 178  | 0.0224         |
+| 3.6    | 180  | 0.0224         |
+| 3.64   | 182  | 0.0224         |
+| 3.68   | 184  | 0.0225         |
+| 3.7200 | 186  | 0.0225         |
+| 3.76   | 188  | 0.0225         |
+| 3.8    | 190  | 0.0225         |
+| 3.84   | 192  | 0.0225         |
+| 3.88   | 194  | 0.0225         |
+| 3.92   | 196  | 0.0226         |
+| 3.96   | 198  | 0.0226         |
+| 4.0    | 200  | 0.0226         |
+| 4.04   | 202  | 0.0226         |
+| 4.08   | 204  | 0.0226         |
+| 4.12   | 206  | 0.0226         |
+| 4.16   | 208  | 0.0225         |
+| 4.2    | 210  | 0.0225         |
+| 4.24   | 212  | 0.0225         |
+| 4.28   | 214  | 0.0225         |
+| 4.32   | 216  | 0.0225         |
+| 4.36   | 218  | 0.0226         |
+| 4.4    | 220  | 0.0227         |
+
+</details>
+
+### Framework Versions
+- Python: 3.10.9
+- Sentence Transformers: 3.0.1
+- Transformers: 4.44.0
+- PyTorch: 2.4.0+cu121
+- Accelerate: 0.33.0
+- Datasets: 2.20.0
+- 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",
+}
+```
+
+#### 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": "BAAI/bge-small-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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": "4.44.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.44.0",
+    "pytorch": "2.4.0+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 sha256:076fc63febba0cc87ba58c5dd73d33fa4030cd3f99545e729c84cd9aec36a329
+size 133462128

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

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

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}