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 +1,451 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:2382
+- loss:MultipleNegativesRankingLoss
+base_model: nomic-ai/nomic-embed-text-v1
+widget:
+- source_sentence: Collect the details that are associated with product '- Com espessura
+    constante de' '- 0,04 m', with quantity 1900, unit M2
+  sentences:
+  - 'Item Description: UNKNOWN PRODUCT, priced at 949.00 EUR, Origin: National'
+  - 'Product: UNKNOWN PRODUCT, Estimated Value: 514.00 EUR'
+  - "Details for 'MacBook Pro 14\" Processador M2/3 16GB/18GB RAM | SSD 512GB | Teclado\
+    \ Es-Es', with quantity 1, unit UN:\n  - LOTE 31\n  - Price: 656.00 EUR"
+- source_sentence: Collect the details that are associated with Lot 14 product ''
+    'Monitor de Sinais Vitais ', with quantity 2, unit Subcontracting Unit
+  sentences:
+  - "Details for 'Monitor de Sinais Vitais ', with quantity 2, unit Subcontracting\
+    \ Unit:\n  - LOTE 60\n  - Price: 564.00 EUR"
+  - "Details for UNKNOWN PRODUCT:\n  - LOTE 90\n  - Price: 658.00 EUR"
+  - 'Item Description: UNKNOWN PRODUCT, priced at 90.00 EUR, Origin: National'
+- source_sentence: Collect the details that are associated with product '' '2202000270
+    - FIO SUT. AC. POLIGLIC. ABS. RÁPIDA 4/0 MULTIF AG. CILIND. 17 MM 1/2 C (UNID)',
+    with quantity 288, unit UN
+  sentences:
+  - 'Item Description: ''2202000270 - FIO SUT. AC. POLIGLIC. ABS. RÁPIDA 4/0 MULTIF
+    AG. CILIND. 17 MM 1/2 C (UNID)'', with quantity 288, unit UN, priced at 66.00
+    EUR, Origin: National'
+  - 'Product: ''2202000285 - FIO SUT. POLIPROPI. NÃO ABS. 4/0 MONOF. AG. LANC. 16
+    MM 3/8 (UNID)'', with quantity 468, unit UN, Estimated Value: 619.00 EUR'
+  - 'Item Description: ''Carro transporte de roupa limpa/roupa suja'', with quantity
+    1, unit Subcontracting Unit, priced at 574.00 EUR, Origin: National'
+- source_sentence: Collect the details that are associated with product '' '2202000006
+    - FIO SUT. SEDA NÃO ABS. 0 MULTIF. SEM AGULHA (CART.)', with quantity 72, unit
+    UN
+  sentences:
+  - 'Item Description: ''2202000309 - FIO SUT. ABS. MÉDIO PRAZO 2/0 MONOF. BARBADO,
+    C/ AG. CILIND. 30MM 1/2C, 23CM (CART.)'', with quantity 24, unit UN, priced at
+    206.00 EUR, Origin: National'
+  - "Details for '2202000006 - FIO SUT. SEDA NÃO ABS. 0 MULTIF. SEM AGULHA (CART.)',\
+    \ with quantity 72, unit UN:\n  - LOTE 82\n  - Price: 854.00 EUR"
+  - 'LOTE 10
+
+    Description: ''Mesas apoio (anestesia e circulante)'', with quantity 4, unit Subcontracting
+    Unit
+
+    Price: 117.00 EUR'
+- source_sentence: Collect the details that are associated with product '' '2202000251
+    - FIO SUT. ABS. LONGA 1 MONOF. AG. CILIND. 48 MM 1/2C 90CM (CART.)', with quantity
+    144, unit UN
+  sentences:
+  - "Details for UNKNOWN PRODUCT:\n  - LOTE 34\n  - Price: 477.00 EUR"
+  - "Details for '2202000251 - FIO SUT. ABS. LONGA 1 MONOF. AG. CILIND. 48 MM 1/2C\
+    \ 90CM (CART.)', with quantity 144, unit UN:\n  - LOTE 73\n  - Price: 644.00 EUR"
+  - 'Item Description: ''Mesas de Mayo'', with quantity 2, unit Subcontracting Unit,
+    priced at 651.00 EUR, Origin: National'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on nomic-ai/nomic-embed-text-v1
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on nomic-ai/nomic-embed-text-v1
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/nomic-embed-text-v1](https://huggingface.co/nomic-ai/nomic-embed-text-v1). 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:** [nomic-ai/nomic-embed-text-v1](https://huggingface.co/nomic-ai/nomic-embed-text-v1) <!-- at revision 720244025c1a7e15661a174c63cce63c8218e52b -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 768 dimensions
+- **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': 8192, 'do_lower_case': False}) with Transformer model: NomicBertModel 
+  (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})
+  (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("ptpedroVortal/nomic_vortal_v3.4")
+# Run inference
+sentences = [
+    "Collect the details that are associated with product '' '2202000251 - FIO SUT. ABS. LONGA 1 MONOF. AG. CILIND. 48 MM 1/2C 90CM (CART.)', with quantity 144, unit UN",
+    "Details for '2202000251 - FIO SUT. ABS. LONGA 1 MONOF. AG. CILIND. 48 MM 1/2C 90CM (CART.)', with quantity 144, unit UN:\n  - LOTE 73\n  - Price: 644.00 EUR",
+    "Item Description: 'Mesas de Mayo', with quantity 2, unit Subcontracting Unit, priced at 651.00 EUR, Origin: National",
+]
+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
+
+#### Semantic Similarity
+
+* Evaluated with <code>__main__.CustomEvaluator</code>
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+
+<!--
+## 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: 2,382 training samples
+* Columns: <code>query</code>, <code>correct_node</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                              | correct_node                                                                         | score                        |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-----------------------------|
+  | type    | string                                                                             | string                                                                               | int                          |
+  | details | <ul><li>min: 15 tokens</li><li>mean: 56.3 tokens</li><li>max: 154 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 49.65 tokens</li><li>max: 1729 tokens</li></ul> | <ul><li>1: 100.00%</li></ul> |
+* Samples:
+  | query                                                                                                                                                                                  | correct_node                                                                                                                                                                | score          |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Collect the details that are associated with product '' '2202000275 - FIO SUT. POLIAMIDA NÃO ABS. 2/0 MONOF AG. CILIND. 30MM 1/2 LOOP (UNID)', with quantity 216, unit UN</code> | <code>LOTE 98<br>Description: '2202000275 - FIO SUT. POLIAMIDA NÃO ABS. 2/0 MONOF AG. CILIND. 30MM 1/2 LOOP (UNID)', with quantity 216, unit UN<br>Price: 940.00 EUR</code> | <code>1</code> |
+  | <code>Collect the details that are associated with product '' '2202000294 - FIO SUT. AC. POLIGLIC. ABS. 2/0 MULTIF SEM AGULHA PRÉ CORTADO (UNID)', with quantity 324, unit UN</code>   | <code>Product: '2202000294 - FIO SUT. AC. POLIGLIC. ABS. 2/0 MULTIF SEM AGULHA PRÉ CORTADO (UNID)', with quantity 324, unit UN, Estimated Value: 696.00 EUR</code>          | <code>1</code> |
+  | <code>Collect the details that are associated with Lot 4 product '' 'Mesas de Mayo', with quantity 2, unit Subcontracting Unit</code>                                                  | <code>LOTE 44<br>Description: 'Mesas de Mayo', with quantity 2, unit Subcontracting Unit<br>Price: 542.00 EUR</code>                                                        | <code>1</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"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 297 evaluation samples
+* Columns: <code>query</code>, <code>correct_node</code>, and <code>score</code>
+* Approximate statistics based on the first 297 samples:
+  |         | query                                                                               | correct_node                                                                        | score                        |
+  |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------|
+  | type    | string                                                                              | string                                                                              | int                          |
+  | details | <ul><li>min: 15 tokens</li><li>mean: 55.37 tokens</li><li>max: 154 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 46.58 tokens</li><li>max: 435 tokens</li></ul> | <ul><li>1: 100.00%</li></ul> |
+* Samples:
+  | query                                                                                                                                                  | correct_node                                                                                                                                       | score          |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Collect the details that are associated with Lot 7 product '' 'Carro transporte de roupa suja', with quantity 1, unit Subcontracting Unit</code> | <code>Item Description: 'Carro transporte de roupa suja', with quantity 1, unit Subcontracting Unit, priced at 628.00 EUR, Origin: National</code> | <code>1</code> |
+  | <code>Collect the details that are associated with Lot 10 product '' 'Mesas para cirurgia', with quantity 2, unit Subcontracting Unit</code>           | <code>Details for 'Mesas para cirurgia', with quantity 2, unit Subcontracting Unit:<br>  - LOTE 83<br>  - Price: 940.00 EUR</code>                 | <code>1</code> |
+  | <code>Collect the details that are associated with Lot 1 product '' 'PAINEL MULTIPLO ALERGENOS RESPIRATORIOS ', with quantity 1152, unit UND</code>    | <code>Product: 'PAINEL MULTIPLO ALERGENOS RESPIRATORIOS ', with quantity 1152, unit UND, Estimated Value: 714.00 EUR</code>                        | <code>1</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`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 10
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `load_best_model_at_end`: 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`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `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`: 1.0
+- `num_train_epochs`: 10
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: 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`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `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 | Validation Loss | spearman_cosine |
+|:----------:|:-------:|:-------------:|:---------------:|:---------------:|
+| 0.6711     | 100     | 0.6485        | 0.4410          | nan             |
+| 1.3356     | 200     | 0.5026        | 0.4399          | nan             |
+| **2.0067** | **300** | **0.491**     | **0.4175**      | **nan**         |
+| 2.6711     | 400     | 0.442         | 0.4409          | nan             |
+| 3.3356     | 500     | 0.3999        | 0.4421          | nan             |
+| 4.0067     | 600     | 0.367         | 0.6182          | nan             |
+| 4.6711     | 700     | 0.3743        | 0.6104          | nan             |
+| 5.3356     | 800     | 0.1972        | 0.6115          | nan             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.3.1
+- Transformers: 4.47.0.dev0
+- PyTorch: 2.5.1+cu121
+- Accelerate: 1.1.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.4
+
+## 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 +1,58 @@
+{
+  "_name_or_path": "nomic-ai/nomic-embed-text-v1",
+  "activation_function": "swiglu",
+  "architectures": [
+    "NomicBertModel"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "nomic-ai/nomic-bert-2048--configuration_hf_nomic_bert.NomicBertConfig",
+    "AutoModel": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertModel",
+    "AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining"
+  },
+  "bos_token_id": null,
+  "causal": false,
+  "dense_seq_output": true,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "fused_bias_fc": true,
+  "fused_dropout_add_ln": true,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-12,
+  "max_trained_positions": 2048,
+  "mlp_fc1_bias": false,
+  "mlp_fc2_bias": false,
+  "model_type": "nomic_bert",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 8192,
+  "pad_vocab_size_multiple": 64,
+  "parallel_block": false,
+  "parallel_block_tied_norm": false,
+  "prenorm": false,
+  "qkv_proj_bias": false,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "rotary_emb_base": 1000,
+  "rotary_emb_fraction": 1.0,
+  "rotary_emb_interleaved": false,
+  "rotary_emb_scale_base": null,
+  "rotary_scaling_factor": 2,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "use_flash_attn": true,
+  "use_rms_norm": false,
+  "use_xentropy": true,
+  "vocab_size": 30528
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.47.0.dev0",
+    "pytorch": "2.5.1+cu121"
+  },
+  "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:e5366ce602da11718a8048449afbaf0d41c0a37c7957b964ec5b7a5d36ad4b91
+size 546938168

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": 8192,
+  "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 +1,56 @@
+{
+  "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_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}