add model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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

@@ -1,3 +1,454 @@
----
-license: apache-2.0
----
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:429643
+- loss:CosineSimilarityLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: Oracle Cloud - Infrastructure and Platform Services for Enterprises
+  sentences:
+  - PulseAudio - Ubuntu Wiki
+  - Documentation page not found - Read the Docs
+  - Dwarf Fortress beginner tips - Video Games on Sports Illustrated
+- source_sentence: Suggest opt in User Test - Google Slides
+  sentences:
+  - ReleaseEngineering/TryServer - MozillaWiki
+  - Dwarf Fortress beginner tips - Video Games on Sports Illustrated
+  - Tutanota - Private Mailbox with End-to-End Encryption and Calendar
+- source_sentence: https://portal.naviabenefits.com/part/prioritytasks.aspx
+  sentences:
+  - What to Expect - Pregnancy and Parenting Tips, Week-by-Week Guides
+  - Parents.com - Articles, Recipes, and Ideas for Family Activities
+  - Pinterest - Boards for Collecting and Sharing Inspiration on Any Topic
+- source_sentence: ‎Apple Music - Web Player
+  sentences:
+  - BMW Connected Drive - Home Assistant
+  - Mary Stewart Phillips (1862-1928) - Find a Grave Memorial
+  - Sky Sports - Football, Formula 1, Cricket, and More
+- source_sentence: Tidal - High-Fidelity Music Streaming with Master Quality Audio
+  sentences:
+  - Walmart - Everyday Low Prices on Groceries, Electronics, and More
+  - Notion - Integrated Workspace for Notes, Tasks, Databases, and Wikis
+  - Ambient Dreams Playlist on Amazon Music
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: pearson_cosine
+      value: 0.9822505655251419
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.2607864200673379
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). 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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision fa97f6e7cb1a59073dff9e6b13e2715cf7475ac9 -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 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': 256, 'do_lower_case': False}) with Transformer model: BertModel
+  (1): Pooling({'word_embedding_dimension': 384, '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("vazish/all-MiniLM-L6-v2-fine-tuned_0")
+# Run inference
+sentences = [
+    'Tidal - High-Fidelity Music Streaming with Master Quality Audio',
+    'Walmart - Everyday Low Prices on Groceries, Electronics, and More',
+    'Notion - Integrated Workspace for Notes, Tasks, Databases, and Wikis',
+]
+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
+
+#### Semantic Similarity
+
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.9823     |
+| **spearman_cosine** | **0.2608** |
+
+<!--
+## 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: 49,800 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                         | sentence_1                                                                         | label                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | float                                                          |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 14.76 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 14.64 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.04</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence_0                                                                        | sentence_1                                                                   | label            |
+  |:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|:-----------------|
+  | <code>TripAdvisor - Hotel Reviews, Photos, and Travel Forums</code>               | <code>Docker Hub - Container Image Repository for DevOps Environments</code> | <code>0.0</code> |
+  | <code>Mastodon - Decentralized Social Media for Niche Communities</code>          | <code>Allrecipes - User-Submitted Recipes, Reviews, and Cooking Tips</code>  | <code>0.0</code> |
+  | <code>YouTube Music - Music Videos, Official Albums, and Live Performances</code> | <code>ESPN - Sports News, Live Scores, Stats, and Highlights</code>          | <code>0.0</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: no
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `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`: 3
+- `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`: 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`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step  | Training Loss | spearman_cosine |
+|:------:|:-----:|:-------------:|:---------------:|
+| 0.0372 | 500   | 0.0218        | -               |
+| 0.0745 | 1000  | 0.0151        | -               |
+| 0.1117 | 1500  | 0.0113        | -               |
+| 0.1490 | 2000  | 0.0076        | -               |
+| 0.1862 | 2500  | 0.0063        | -               |
+| 0.2234 | 3000  | 0.0054        | -               |
+| 0.2607 | 3500  | 0.0045        | -               |
+| 0.2979 | 4000  | 0.0041        | -               |
+| 0.3351 | 4500  | 0.0027        | -               |
+| 0.3724 | 5000  | 0.0028        | -               |
+| 0.4096 | 5500  | 0.0026        | -               |
+| 0.4469 | 6000  | 0.0021        | -               |
+| 0.4841 | 6500  | 0.0019        | -               |
+| 0.5213 | 7000  | 0.0022        | -               |
+| 0.5586 | 7500  | 0.0017        | -               |
+| 0.5958 | 8000  | 0.0018        | -               |
+| 0.6331 | 8500  | 0.0015        | -               |
+| 0.6703 | 9000  | 0.0015        | -               |
+| 0.7075 | 9500  | 0.0018        | -               |
+| 0.7448 | 10000 | 0.0014        | -               |
+| 0.7820 | 10500 | 0.0017        | -               |
+| 0.8192 | 11000 | 0.0012        | -               |
+| 0.8565 | 11500 | 0.0014        | -               |
+| 0.8937 | 12000 | 0.001         | -               |
+| 0.9310 | 12500 | 0.0011        | -               |
+| 0.9682 | 13000 | 0.001         | -               |
+| 1.0054 | 13500 | 0.0009        | -               |
+| 1.0427 | 14000 | 0.0011        | -               |
+| 1.0799 | 14500 | 0.001         | -               |
+| 1.1172 | 15000 | 0.0009        | -               |
+| 1.1544 | 15500 | 0.0008        | -               |
+| 1.1916 | 16000 | 0.001         | -               |
+| 1.2289 | 16500 | 0.0011        | -               |
+| 1.2661 | 17000 | 0.0011        | -               |
+| 1.3033 | 17500 | 0.0006        | -               |
+| 1.3406 | 18000 | 0.0011        | -               |
+| 1.3778 | 18500 | 0.0008        | -               |
+| 1.4151 | 19000 | 0.0011        | -               |
+| 1.4523 | 19500 | 0.0009        | -               |
+| 1.4895 | 20000 | 0.0011        | -               |
+| 1.5268 | 20500 | 0.0009        | -               |
+| 1.5640 | 21000 | 0.0009        | -               |
+| 1.6013 | 21500 | 0.0008        | -               |
+| 1.6385 | 22000 | 0.0005        | -               |
+| 1.6757 | 22500 | 0.001         | -               |
+| 1.7130 | 23000 | 0.0008        | -               |
+| 1.7502 | 23500 | 0.0007        | -               |
+| 1.7874 | 24000 | 0.0007        | -               |
+| 1.8247 | 24500 | 0.0008        | -               |
+| 1.8619 | 25000 | 0.001         | -               |
+| 1.8992 | 25500 | 0.0009        | -               |
+| 1.9364 | 26000 | 0.0008        | -               |
+| 1.9736 | 26500 | 0.0009        | -               |
+| 2.0109 | 27000 | 0.0007        | -               |
+| 2.0481 | 27500 | 0.0006        | -               |
+| 2.0854 | 28000 | 0.0007        | -               |
+| 2.1226 | 28500 | 0.0006        | -               |
+| 2.1598 | 29000 | 0.0007        | -               |
+| 2.1971 | 29500 | 0.001         | -               |
+| 2.2343 | 30000 | 0.0006        | -               |
+| 2.2715 | 30500 | 0.0006        | -               |
+| 2.3088 | 31000 | 0.001         | -               |
+| 2.3460 | 31500 | 0.0007        | -               |
+| 2.3833 | 32000 | 0.0008        | -               |
+| 2.4205 | 32500 | 0.0006        | -               |
+| 2.4577 | 33000 | 0.0007        | -               |
+| 2.4950 | 33500 | 0.0007        | -               |
+| 2.5322 | 34000 | 0.001         | -               |
+| 2.5694 | 34500 | 0.0007        | -               |
+| 2.6067 | 35000 | 0.0007        | -               |
+| 2.6439 | 35500 | 0.0008        | -               |
+| 2.6812 | 36000 | 0.0007        | -               |
+| 2.7184 | 36500 | 0.0006        | -               |
+| 2.7556 | 37000 | 0.0007        | -               |
+| 2.7929 | 37500 | 0.0007        | -               |
+| 2.8301 | 38000 | 0.0005        | -               |
+| 2.8674 | 38500 | 0.0009        | -               |
+| 2.9046 | 39000 | 0.0006        | -               |
+| 2.9418 | 39500 | 0.0007        | -               |
+| 2.9791 | 40000 | 0.0008        | -               |
+| -1     | -1    | -             | 0.2608          |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.48.2
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.2.0
+- 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",
+}
+```
+
+<!--
+## 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 +1,28 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "/content/model",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "export_model_type": "transformer",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.2",
+    "pytorch": "2.5.1+cu124"
+  },
+  "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:cce795656a2f5901d70c4ea6568b7c98a136a9f653ec4e8e499ac26270beffcb
+size 90864192

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"
+  }
+]

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506ac8fdb54c3d5401fc03fb7cc135553857779e2cc518dfb3341cf113ebe257
+size 90448255

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77f96020b60846dbd7f86538280364c6f5e7d1fce2a1753debe0fa28a5b2a1dc
+size 53958494

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:492935c401e7ae513a959c9433dd204f159b501593bf732507b94d73081ae14d
+size 45317631

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8575a3ba5d8a44884f56579d2046d5883e4bbef1923840f7b6b561bc6a6918
+size 22999753

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235764145072d6bc5e6ab9f61f17e893f47dd02cc6eef3a5a1967fbfbae31523
+size 54621818

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a462c3bbf68ad9d80c3367342d67fba38b871f683bd78a741479e9df6017dba
+size 30061282

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8575a3ba5d8a44884f56579d2046d5883e4bbef1923840f7b6b561bc6a6918
+size 22999753

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d985ea995e76faa0d7f542db38a3e08ecfedfc8b9cfa1143e8c13398803019d
+size 22999753

quantize_config.json

@@ -0,0 +1,18 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": true,
+    "reduce_range": true,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "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 +1,65 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}