Upload folder using huggingface_hub

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

@@ -1,3 +1,469 @@
----
-license: apache-2.0
----
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:1195425
+- loss:MSELoss
+base_model: mixedbread-ai/mxbai-embed-large-v1
+widget:
+- source_sentence: At an outdoor event in an Asian-themed area, a crowd congregates
+    as one person in a yellow Chinese dragon costume confronts the camera.
+  sentences:
+  - Boy dressed in blue holds a toy.
+  - A man is smiling at his wife.
+  - Two young asian men are squatting.
+- source_sentence: A man with a shopping cart is studying the shelves in a supermarket
+    aisle.
+  sentences:
+  - the animal is running
+  - The children are watching TV at home.
+  - Three young boys one is holding a camera and another is holding a green toy all
+    are wearing t-shirt and smiling.
+- source_sentence: The door is open.
+  sentences:
+  - A girl is using an apple laptop with her headphones in her ears.
+  - There are three men in this picture, two are on motorbikes, one of the men has
+    a large piece of furniture on the back of his bike, the other is about to be handed
+    a piece of paper by a man in a white shirt.
+  - A large group of people are gathered outside of a brick building lit with spotlights.
+- source_sentence: A small group of children are standing in a classroom and one of
+    them has a foot in a trashcan, which also has a rope leading out of it.
+  sentences:
+  - People are playing music.
+  - Children are swimming at the beach.
+  - Women are celebrating at a bar.
+- source_sentence: A black dog is drinking next to a brown and white dog that is looking
+    at an orange ball in the lake, whilst a horse and rider passes behind.
+  sentences:
+  - Some men with jerseys are in a bar, watching a soccer match.
+  - the guy is dead
+  - There are two people running around a track in lane three and the one wearing
+    a blue shirt with a green thing over the eyes is just barely ahead of the guy
+    wearing an orange shirt and sunglasses.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+- negative_mse
+model-index:
+- name: SentenceTransformer based on mixedbread-ai/mxbai-embed-large-v1
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.8654028138219636
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8873087539713633
+      name: Spearman Cosine
+  - task:
+      type: knowledge-distillation
+      name: Knowledge Distillation
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: negative_mse
+      value: -3.3795181661844254
+      name: Negative Mse
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.834023412201456
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8723901159121923
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on mixedbread-ai/mxbai-embed-large-v1
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1). 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:** [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) <!-- at revision e7857440379da569f68f19e8403b69cd7be26e50 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 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': 512, 'do_lower_case': False}) 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})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'A black dog is drinking next to a brown and white dog that is looking at an orange ball in the lake, whilst a horse and rider passes behind.',
+    'Some men with jerseys are in a bar, watching a soccer match.',
+    'There are two people running around a track in lane three and the one wearing a blue shirt with a green thing over the eyes is just barely ahead of the guy wearing an orange shirt and sunglasses.',
+]
+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
+
+* Datasets: `sts-dev` and `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | sts-dev    | sts-test   |
+|:--------------------|:-----------|:-----------|
+| pearson_cosine      | 0.8654     | 0.834      |
+| **spearman_cosine** | **0.8873** | **0.8724** |
+
+#### Knowledge Distillation
+
+* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.MSEEvaluator)
+
+| Metric           | Value       |
+|:-----------------|:------------|
+| **negative_mse** | **-3.3795** |
+
+<!--
+## 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: 1,195,425 training samples
+* Columns: <code>sentence</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence                                                                          | label                                 |
+  |:--------|:----------------------------------------------------------------------------------|:--------------------------------------|
+  | type    | string                                                                            | list                                  |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 12.24 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>size: 1024 elements</li></ul> |
+* Samples:
+  | sentence                                                                   | label                                                                                                                      |
+  |:---------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------|
+  | <code>A person on a horse jumps over a broken down airplane.</code>        | <code>[-0.012967385351657867, 0.3716000020503998, 0.252520889043808, 0.7052643299102783, -0.15118499100208282, ...]</code> |
+  | <code>Children smiling and waving at camera</code>                         | <code>[0.15414997935295105, 0.6666896939277649, -0.3150098919868469, 1.0102407932281494, 0.4113735556602478, ...]</code>   |
+  | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>[-0.2989530563354492, 0.8571284413337708, -0.48532426357269287, 0.8935043215751648, 0.28524795174598694, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#mseloss)
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 10,000 evaluation samples
+* Columns: <code>sentence</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence                                                                          | label                                 |
+  |:--------|:----------------------------------------------------------------------------------|:--------------------------------------|
+  | type    | string                                                                            | list                                  |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 13.23 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>size: 1024 elements</li></ul> |
+* Samples:
+  | sentence                                                                                                                                                                       | label                                                                                                                       |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------|
+  | <code>Two women are embracing while holding to go packages.</code>                                                                                                             | <code>[-0.35094621777534485, 0.4337681233882904, 0.22905530035495758, 0.9438946843147278, -1.0199058055877686, ...]</code>  |
+  | <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>[-0.37593328952789307, 0.6690596342086792, -0.14921458065509796, 0.7559019923210144, -0.4093412756919861, ...]</code> |
+  | <code>A man selling donuts to a customer during a world exhibition event held in the city of Angeles</code>                                                                    | <code>[0.21969863772392273, 0.5065202713012695, -0.25664886832237244, 0.2569092810153961, -0.05940837413072586, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#mseloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `learning_rate`: 0.0001
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: 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`: 64
+- `per_device_eval_batch_size`: 64
+- `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`: 0.0001
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `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`: 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`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch     | Step      | Training Loss | Validation Loss | sts-dev_spearman_cosine | negative_mse | sts-test_spearman_cosine |
+|:---------:|:---------:|:-------------:|:---------------:|:-----------------------:|:------------:|:------------------------:|
+| 0         | 0         | -             | -               | 0.5276                  | -38.5866     | -                        |
+| 0.0535    | 1000      | 0.1759        | -               | -                       | -            | -                        |
+| 0.1071    | 2000      | 0.0992        | -               | -                       | -            | -                        |
+| 0.1606    | 3000      | 0.0773        | -               | -                       | -            | -                        |
+| 0.2141    | 4000      | 0.0669        | -               | -                       | -            | -                        |
+| 0.2677    | 5000      | 0.0607        | 0.0502          | 0.8761                  | -5.0231      | -                        |
+| 0.3212    | 6000      | 0.0563        | -               | -                       | -            | -                        |
+| 0.3748    | 7000      | 0.053         | -               | -                       | -            | -                        |
+| 0.4283    | 8000      | 0.0502        | -               | -                       | -            | -                        |
+| 0.4818    | 9000      | 0.0481        | -               | -                       | -            | -                        |
+| 0.5354    | 10000     | 0.0464        | 0.0388          | 0.8830                  | -3.8785      | -                        |
+| 0.5889    | 11000     | 0.0448        | -               | -                       | -            | -                        |
+| 0.6424    | 12000     | 0.0434        | -               | -                       | -            | -                        |
+| 0.6960    | 13000     | 0.0422        | -               | -                       | -            | -                        |
+| 0.7495    | 14000     | 0.0414        | -               | -                       | -            | -                        |
+| **0.803** | **15000** | **0.0405**    | **0.0338**      | **0.8873**              | **-3.3795**  | **-**                    |
+| 0.8566    | 16000     | 0.0398        | -               | -                       | -            | -                        |
+| 0.9101    | 17000     | 0.0392        | -               | -                       | -            | -                        |
+| 0.9636    | 18000     | 0.039         | -               | -                       | -            | -                        |
+| 1.0       | 18679     | -             | -               | -                       | -            | 0.8724                   |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.3.1
+- Transformers: 4.46.3
+- PyTorch: 2.4.0
+- Accelerate: 1.1.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## 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",
+}
+```
+
+#### MSELoss
+```bibtex
+@inproceedings{reimers-2020-multilingual-sentence-bert,
+    title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2020",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/2004.09813",
+}
+```
+
+<!--
+## 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": "mixedbread-ai/mxbai-embed-large-v1",
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 8,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,13 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.46.3",
+    "pytorch": "2.4.0"
+  },
+  "prompts": {
+    "query": "Represent this sentence for searching relevant passages: ",
+    "passage": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df516c281745e0401509d5f5262fb5fb9aada3cfa641f813c808c5b7e333da3f
+size 534424512

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

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 +1,57 @@
+{
+  "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]"
+}