Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "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 +1,587 @@
+---
+base_model: Snowflake/snowflake-arctic-embed-m
+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:600
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Which entities are responsible for enforcing the requirements discussed
+    in the context?
+  sentences:
+  - 'ALGORITHMIC DISCRIMINATION PROTECTIONS
+
+    You should not face discrimination by algorithms and systems should be used and
+    designed in'
+  - 'SECTION TITLE
+
+    HUMAN ALTERNATIVES, CONSIDERATION, AND FALLBACK
+
+    You should be able to opt out, where appropriate, and have access to a person
+    who can quickly'
+  - requirements of the Federal agencies that enforce them. These principles are not
+    intended to, and do not,
+- source_sentence: How is safety addressed in the development process according to
+    the context?
+  sentences:
+  - "TABLE OF CONTENTS\nFROM PRINCIPLES TO PRACTICE: A TECHNICAL COMPANION TO THE\
+    \ BLUEPRINT \nFOR AN AI BILL OF RIGHTS \n \nUSING THIS TECHNICAL COMPANION\n \n\
+    SAFE AND EFFECTIVE SYSTEMS"
+  - "stemming from unintended, yet foreseeable, uses or \n \n \n \n \n  \n \n \nSECTION\
+    \ TITLE\nBLUEPRINT FOR AN\nSAFE AND E \nYou should be protected from unsafe or\
+    \ \ndeveloped with consultation from diverse"
+  - tion or implemented under existing U.S. laws. For example, government surveillance,
+    and data search and
+- source_sentence: How should the deployment of automated systems be aligned with
+    the principles for protecting the American public?
+  sentences:
+  - "public and private sector contexts; \nEqual opportunities, including equitable\
+    \ access to education, housing, credit, employment, and other \nprograms; or,"
+  - use, and deployment of automated systems to protect the rights of the American
+    public in the age of artificial
+  - five principles that should guide the design, use, and deployment of automated
+    systems to protect the American
+- source_sentence: Who should designers, developers, and deployers of automated systems
+    seek permission from?
+  sentences:
+  - This important progress must not come at the price of civil rights or democratic
+    values, foundational American
+  - a blueprint for building and deploying automated systems that are aligned with
+    democratic values and protect
+  - context is collected. Designers, developers, and deployers of automated systems
+    should seek your permission
+- source_sentence: What changes are suggested for notice-and-choice practices regarding
+    broad uses of data?
+  sentences:
+  - mated systems, and researchers developing innovative guardrails. Advocates, researchers,
+    and government
+  - tial to meaningfully impact rights, opportunities, or access. Additionally, this
+    framework does not analyze or
+  - understand notice-and-choice practices for broad uses of data should be changed.
+    Enhanced protections and
+model-index:
+- name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-m
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.99
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.99
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.33000000000000007
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19799999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09999999999999998
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.9
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.99
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.99
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9601170111547646
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9464285714285714
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9464285714285714
+      name: Cosine Map@100
+    - type: dot_accuracy@1
+      value: 0.9
+      name: Dot Accuracy@1
+    - type: dot_accuracy@3
+      value: 0.99
+      name: Dot Accuracy@3
+    - type: dot_accuracy@5
+      value: 0.99
+      name: Dot Accuracy@5
+    - type: dot_accuracy@10
+      value: 1.0
+      name: Dot Accuracy@10
+    - type: dot_precision@1
+      value: 0.9
+      name: Dot Precision@1
+    - type: dot_precision@3
+      value: 0.33000000000000007
+      name: Dot Precision@3
+    - type: dot_precision@5
+      value: 0.19799999999999998
+      name: Dot Precision@5
+    - type: dot_precision@10
+      value: 0.09999999999999998
+      name: Dot Precision@10
+    - type: dot_recall@1
+      value: 0.9
+      name: Dot Recall@1
+    - type: dot_recall@3
+      value: 0.99
+      name: Dot Recall@3
+    - type: dot_recall@5
+      value: 0.99
+      name: Dot Recall@5
+    - type: dot_recall@10
+      value: 1.0
+      name: Dot Recall@10
+    - type: dot_ndcg@10
+      value: 0.9601170111547646
+      name: Dot Ndcg@10
+    - type: dot_mrr@10
+      value: 0.9464285714285714
+      name: Dot Mrr@10
+    - type: dot_map@100
+      value: 0.9464285714285714
+      name: Dot Map@100
+---
+
+# SentenceTransformer based on Snowflake/snowflake-arctic-embed-m
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-m](https://huggingface.co/Snowflake/snowflake-arctic-embed-m). 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:** [Snowflake/snowflake-arctic-embed-m](https://huggingface.co/Snowflake/snowflake-arctic-embed-m) <!-- at revision e2b128b9fa60c82b4585512b33e1544224ffff42 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 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': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, '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("dstampfli/finetuned-snowflake-arctic-embed-m")
+# Run inference
+sentences = [
+    'What changes are suggested for notice-and-choice practices regarding broad uses of data?',
+    'understand notice-and-choice practices for broad uses of data should be changed. Enhanced protections and',
+    'tial to meaningfully impact rights, opportunities, or access. Additionally, this framework does not analyze or',
+]
+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
+
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.9        |
+| cosine_accuracy@3   | 0.99       |
+| cosine_accuracy@5   | 0.99       |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.9        |
+| cosine_precision@3  | 0.33       |
+| cosine_precision@5  | 0.198      |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.9        |
+| cosine_recall@3     | 0.99       |
+| cosine_recall@5     | 0.99       |
+| cosine_recall@10    | 1.0        |
+| cosine_ndcg@10      | 0.9601     |
+| cosine_mrr@10       | 0.9464     |
+| **cosine_map@100**  | **0.9464** |
+| dot_accuracy@1      | 0.9        |
+| dot_accuracy@3      | 0.99       |
+| dot_accuracy@5      | 0.99       |
+| dot_accuracy@10     | 1.0        |
+| dot_precision@1     | 0.9        |
+| dot_precision@3     | 0.33       |
+| dot_precision@5     | 0.198      |
+| dot_precision@10    | 0.1        |
+| dot_recall@1        | 0.9        |
+| dot_recall@3        | 0.99       |
+| dot_recall@5        | 0.99       |
+| dot_recall@10       | 1.0        |
+| dot_ndcg@10         | 0.9601     |
+| dot_mrr@10          | 0.9464     |
+| dot_map@100         | 0.9464     |
+
+<!--
+## 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: 600 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 600 samples:
+  |         | sentence_0                                                                        | sentence_1                                                                        |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 9 tokens</li><li>mean: 17.15 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 23.93 tokens</li><li>max: 46 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                          | sentence_1                                                                                                                                 |
+  |:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>What is the purpose of the AI Bill of Rights mentioned in the context?</code> | <code>BLUEPRINT FOR AN <br>AI BILL OF <br>RIGHTS <br>MAKING AUTOMATED <br>SYSTEMS WORK FOR <br>THE AMERICAN PEOPLE <br>OCTOBER 2022</code> |
+  | <code>When was the Blueprint for an AI Bill of Rights published?</code>             | <code>BLUEPRINT FOR AN <br>AI BILL OF <br>RIGHTS <br>MAKING AUTOMATED <br>SYSTEMS WORK FOR <br>THE AMERICAN PEOPLE <br>OCTOBER 2022</code> |
+  | <code>What is the main purpose of the Blueprint for an AI Bill of Rights?</code>    | <code>About this Document <br>The Blueprint for an AI Bill of Rights: Making Automated Systems Work for the American People was</code>     |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 20
+- `per_device_eval_batch_size`: 20
+- `num_train_epochs`: 5
+- `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`: 20
+- `per_device_eval_batch_size`: 20
+- `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`: 5
+- `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
+| Epoch  | Step | cosine_map@100 |
+|:------:|:----:|:--------------:|
+| 1.0    | 30   | 0.9458         |
+| 1.6667 | 50   | 0.9461         |
+| 2.0    | 60   | 0.9461         |
+| 3.0    | 90   | 0.9463         |
+| 3.3333 | 100  | 0.9463         |
+| 4.0    | 120  | 0.9464         |
+| 5.0    | 150  | 0.9464         |
+
+
+### Framework Versions
+- Python: 3.11.9
+- Sentence Transformers: 3.1.1
+- Transformers: 4.44.2
+- PyTorch: 2.4.1
+- Accelerate: 0.34.2
+- Datasets: 3.0.0
+- 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning},
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "Snowflake/snowflake-arctic-embed-m",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "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": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,12 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.4.1"
+  },
+  "prompts": {
+    "query": "Represent this sentence for searching relevant passages: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df63ef854daef96c3b4802c2047d0505f9c389e615d49ebce4fed889027fc25b
+size 435588776

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": 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 +1,62 @@
+{
+  "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,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "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]"
+}