Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "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 +1,465 @@
+---
+base_model: BAAI/bge-large-en-v1.5
+datasets: []
+language: []
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:132
+- loss:CoSENTLoss
+widget:
+- source_sentence: A person shall have 3045 days after commencing business within
+    the City to apply for a registration certificate.
+  sentences:
+  - The new transportation plan replaces the previous one approved by San Francisco
+    voters in 2003. |
+  - The Department of Elections is revising sections of its definitions and deleting
+    a section to operate definitions for Article 12. |
+  - A newly-established business shall have 3045 days after commencing business within
+    the City to apply for a registration certificate, and the registration fee for
+    such businesses shall be prorated based on the estimated gross receipts for the
+    tax year in which the business commences.
+- source_sentence: The homelessness gross receipts tax is a privilege tax imposed
+    upon persons engaging in business within the City for the privilege of engaging
+    in a business or occupation in the City. |
+  sentences:
+  - The City imposes an annual Homelessness Gross Receipts Tax on businesses with
+    more than $50,000,000 in total taxable gross receipts. |
+  - The tax on Administrative Office Business Activities imposed by Section 2804.9
+    is intended as a complementary tax to the homelessness gross receipts tax, and
+    shall be considered a homelessness gross receipts tax for purposes of this Article
+    28. |
+  - '"The 5YPPs shall at a minimum address the following factors: compatibility with
+    existing and planned land uses, and with adopted standards for urban design and
+    for the provision of pedestrian amenities; and supportiveness of planned growth
+    in transit-friendly housing, employment, and services." |'
+- source_sentence: '"The total worldwide compensation paid by the person and all related
+    entities to the person is referred to as combined payroll." |'
+  sentences:
+  - '"A taxpayer is eligible to claim a credit against their immediately succeeding
+    payments due for tax years or periods ending on or before December 31, 2024, of
+    the respective tax type by applying all or part of an overpayment of the Homelessness
+    Gross Receipts Tax in Article 28 (including the homelessness administrative office
+    tax under Section 2804(d) of Article 28)." |'
+  - '"Receipts from the sale of real property are exempt from the gross receipts tax
+    if the Real Property Transfer Tax imposed by Article 12-C has been paid to the
+    City."'
+  - '"The total amount paid for compensation in the City by the person and by all
+    related entities to the person is referred to as payroll in the City." |'
+- source_sentence: '"The gross receipts tax rates applicable to Category 6 Business
+    Activities are determined based on the amount of taxable gross receipts from these
+    activities." |'
+  sentences:
+  - '"The project meets the criteria outlined in Section 131051(d) of the Public Utilities
+    Code."'
+  - For the business activity of clean technology, a tax rate of 0.175% (e.g. $1.75
+    per $1,000) applies to taxable gross receipts between $0 and $1,000,000 for tax
+    years beginning on or after January 1, 2021 through and including 2024. |
+  - '"The tax rates for Category 7 Business Activities are also determined based on
+    the amount of taxable gross receipts." |'
+- source_sentence: '"Compensation" refers to wages, salaries, commissions, bonuses,
+    and property issued or transferred in exchange for services, as well as compensation
+    for services to owners of pass-through entities, and any other form of remuneration
+    paid to employees for services.'
+  sentences:
+  - '"Every person engaging in business within the City as an administrative office,
+    as defined below, shall pay an annual administrative office tax measured by its
+    total payroll expense that is attributable to the City:" |'
+  - '"Remuneration" refers to any payment or reward, including but not limited to
+    wages, salaries, commissions, bonuses, and property issued or transferred in exchange
+    for services, as well as compensation for services to owners of pass-through entities,
+    and any other form of compensation paid to employees for services.'
+  - '"Construction of new Americans with Disabilities Act (ADA)-compliant curb ramps
+    and related roadway work to permit ease of movement." |'
+model-index:
+- name: SentenceTransformer based on BAAI/bge-large-en-v1.5
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: pearson_cosine
+      value: 0.3338547038124495
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.41279297374061835
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.3102979152053135
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.41673878893078603
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.30953937257079917
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.41279297374061835
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.3338548430968143
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.41279297374061835
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.3338548430968143
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.41673878893078603
+      name: Spearman Max
+---
+
+# SentenceTransformer based on BAAI/bge-large-en-v1.5
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5). It maps sentences & paragraphs to a 1024-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-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) <!-- at revision d4aa6901d3a41ba39fb536a557fa166f842b0e09 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 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': 1024, '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("Areeb-02/bge-large-en-v1.5-CosentLoss")
+# Run inference
+sentences = [
+    '"Compensation" refers to wages, salaries, commissions, bonuses, and property issued or transferred in exchange for services, as well as compensation for services to owners of pass-through entities, and any other form of remuneration paid to employees for services.',
+    '"Remuneration" refers to any payment or reward, including but not limited to wages, salaries, commissions, bonuses, and property issued or transferred in exchange for services, as well as compensation for services to owners of pass-through entities, and any other form of compensation paid to employees for services.',
+    '"Every person engaging in business within the City as an administrative office, as defined below, shall pay an annual administrative office tax measured by its total payroll expense that is attributable to the City:" |',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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      | 0.3339     |
+| **spearman_cosine** | **0.4128** |
+| pearson_manhattan   | 0.3103     |
+| spearman_manhattan  | 0.4167     |
+| pearson_euclidean   | 0.3095     |
+| spearman_euclidean  | 0.4128     |
+| pearson_dot         | 0.3339     |
+| spearman_dot        | 0.4128     |
+| pearson_max         | 0.3339     |
+| spearman_max        | 0.4167     |
+
+<!--
+## 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: 132 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                           | sentence2                                                                           | score                                                           |
+  |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                              | float                                                           |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 41.99 tokens</li><li>max: 126 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 42.72 tokens</li><li>max: 162 tokens</li></ul> | <ul><li>min: 0.25</li><li>mean: 0.93</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | sentence2                                                                                                                                                                                                                                        | score             |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------|
+  | <code>"Gross receipts as defined in Section 952.3 shall not include receipts from any sales of real property with respect to which the Real Property Transfer Tax imposed by Article 12-C has been paid to the City."</code>                                                                                                                                                                                                                                                                                                                                                                                       | <code>"Receipts from the sale of real property are exempt from the gross receipts tax if the Real Property Transfer Tax imposed by Article 12-C has been paid to the City."</code>                                                               | <code>1.0</code>  |
+  | <code>For tax years beginning on or after January 1, 2025, any person or combined group, except for a lessor of residential real estate, whose gross receipts within the City did not exceed $5,000,000, adjusted annually in accordance with the increase in the Consumer Price Index: All Urban Consumers for the San Francisco/Oakland/Hayward Area for All Items as reported by the United States Bureau of Labor Statistics, or any successor to that index, as of December 31 of the calendar year two years prior to the tax year, beginning with tax year 2026, and rounded to the nearest $10,000.</code> | <code>For taxable years ending on or before December 31, 2024, using the rules set forth in Sections 956.1 and 956.2, in the manner directed in Sections 953.1 through 953.7, inclusive, and in Section 953.9 of this Article 12-A-1; and</code> | <code>0.95</code> |
+  | <code>"San Francisco Gross Receipts" refers to the revenue generated from sales and services within the city limits of San Francisco.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                       | <code>"Revenue generated from sales and services within the city limits of San Francisco"</code>                                                                                                                                                 | <code>1.0</code>  |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_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`: 5
+- `warmup_ratio`: 0.1
+- `fp16`: True
+
+#### 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
+- `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`: 5
+- `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`: False
+- `fp16`: True
+- `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
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch | Step | spearman_cosine |
+|:-----:|:----:|:---------------:|
+| 3.0   | 51   | 0.4078          |
+| 5.0   | 45   | 0.4128          |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.0.dev0
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.31.0
+- Datasets: 2.19.2
+- 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",
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## 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 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-large-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "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": "4.42.0.dev0",
+    "pytorch": "2.3.0+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:fa897fc8821e685d7452d8577b3d10ad3c9af1b204eb30aa5910c77e191f8c38
+size 1340612432

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]"
+}