Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,566 @@
+---
+base_model: google-bert/bert-base-uncased
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- manhattan_accuracy
+- manhattan_accuracy_threshold
+- manhattan_f1
+- manhattan_f1_threshold
+- manhattan_precision
+- manhattan_recall
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_accuracy_threshold
+- euclidean_f1
+- euclidean_f1_threshold
+- euclidean_precision
+- euclidean_recall
+- euclidean_ap
+- max_accuracy
+- max_accuracy_threshold
+- max_f1
+- max_f1_threshold
+- max_precision
+- max_recall
+- max_ap
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:103663
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: How much native Icelandic and advanced Icelandic learners can read
+    and understand Old Norse?
+  sentences:
+  - What are the best answers for "Why should I hire you?"in a cool way?
+  - Are girls shy in expressing their feelings?
+  - If I learn Icelandic can I understand old norse texts?
+- source_sentence: Where can I get quality assistance for budget conveyancing across
+    the Sydney?
+  sentences:
+  - What are the possible options for India to deal with Uri terror attack?
+  - What is the intended purpose of philosophy?
+  - Where can I get quality assistance in Sydney for any property transaction?
+- source_sentence: What are some of the best IAS coaching institutions in Mumbai?
+  sentences:
+  - What are best IAS coaching institutes in Mumbai?
+  - Do vampires really exist?
+  - What do most women feel during sex?
+- source_sentence: Is petroleum engineering still a good major?
+  sentences:
+  - What are some of the best sex stories?
+  - Can I clear CAT in 4.5 months?
+  - What is the future of petroleum engineering graduating in 2020?
+- source_sentence: How can the drive from Edmonton to Auckland be described, and how
+    do these cities' attractions compare to those in Vancouver?
+  sentences:
+  - How can the drive from Edmonton to Auckland be described, and how does the history
+    of these cities compare and contrast to the history of Vancouver?
+  - What are the best hashtags to use as a photographer on instagram?
+  - Which optional subjects can I choose for the IAS exam?
+model-index:
+- name: SentenceTransformer based on google-bert/bert-base-uncased
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy
+      value: 0.7643828947012523
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.8147265911102295
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.6959193470955354
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7402496337890625
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.5945532101060921
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.838953622964735
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.7112611713824615
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.7399583457304374
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 153.5009765625
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.6710917251406536
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 133.23265075683594
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.5683387761657477
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.8191990122694652
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.6542447011722929
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.7665197046333613
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 176.4288787841797
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.6972882533068157
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 218.96762084960938
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.590020301314243
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.8522262520256193
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.7109056366977289
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.7665197046333613
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 8.092199325561523
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.6970045347129081
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 9.794208526611328
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.5945518932171071
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.8421174473338993
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.7109417385930392
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.7665197046333613
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 176.4288787841797
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.6972882533068157
+      name: Max F1
+    - type: max_f1_threshold
+      value: 218.96762084960938
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.5945532101060921
+      name: Max Precision
+    - type: max_recall
+      value: 0.8522262520256193
+      name: Max Recall
+    - type: max_ap
+      value: 0.7112611713824615
+      name: Max Ap
+---
+
+# SentenceTransformer based on google-bert/bert-base-uncased
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased). 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:** [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) <!-- at revision 86b5e0934494bd15c9632b12f734a8a67f723594 -->
+- **Maximum Sequence Length:** 128 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': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## 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("gavinqiangli/my-awesome-bi-encoder")
+# Run inference
+sentences = [
+    "How can the drive from Edmonton to Auckland be described, and how do these cities' attractions compare to those in Vancouver?",
+    'How can the drive from Edmonton to Auckland be described, and how does the history of these cities compare and contrast to the history of Vancouver?',
+    'Which optional subjects can I choose for the IAS exam?',
+]
+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
+
+#### Binary Classification
+
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.7644     |
+| cosine_accuracy_threshold    | 0.8147     |
+| cosine_f1                    | 0.6959     |
+| cosine_f1_threshold          | 0.7402     |
+| cosine_precision             | 0.5946     |
+| cosine_recall                | 0.839      |
+| cosine_ap                    | 0.7113     |
+| dot_accuracy                 | 0.74       |
+| dot_accuracy_threshold       | 153.501    |
+| dot_f1                       | 0.6711     |
+| dot_f1_threshold             | 133.2327   |
+| dot_precision                | 0.5683     |
+| dot_recall                   | 0.8192     |
+| dot_ap                       | 0.6542     |
+| manhattan_accuracy           | 0.7665     |
+| manhattan_accuracy_threshold | 176.4289   |
+| manhattan_f1                 | 0.6973     |
+| manhattan_f1_threshold       | 218.9676   |
+| manhattan_precision          | 0.59       |
+| manhattan_recall             | 0.8522     |
+| manhattan_ap                 | 0.7109     |
+| euclidean_accuracy           | 0.7665     |
+| euclidean_accuracy_threshold | 8.0922     |
+| euclidean_f1                 | 0.697      |
+| euclidean_f1_threshold       | 9.7942     |
+| euclidean_precision          | 0.5946     |
+| euclidean_recall             | 0.8421     |
+| euclidean_ap                 | 0.7109     |
+| max_accuracy                 | 0.7665     |
+| max_accuracy_threshold       | 176.4289   |
+| max_f1                       | 0.6973     |
+| max_f1_threshold             | 218.9676   |
+| max_precision                | 0.5946     |
+| max_recall                   | 0.8522     |
+| **max_ap**                   | **0.7113** |
+
+<!--
+## 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: 103,663 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                                                                            | int                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 13.82 tokens</li><li>max: 41 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 13.87 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>0: ~4.80%</li><li>1: ~95.20%</li></ul> |
+* Samples:
+  | sentence_0                                                                           | sentence_1                                               | label          |
+  |:-------------------------------------------------------------------------------------|:---------------------------------------------------------|:---------------|
+  | <code>Are Jewish people the most intelligent in the universe?</code>                 | <code>Why are Jewish people so intelligent?</code>       | <code>1</code> |
+  | <code>How do I become a good lawyer? What are the qualities of a good lawyer?</code> | <code>How can someone become a successful lawyer?</code> | <code>1</code> |
+  | <code>Why is China going to the Moon?</code>                                         | <code>What does China want with the moon?</code>         | <code>1</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 1
+- `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`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 1
+- `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 | Training Loss | max_ap |
+|:------:|:----:|:-------------:|:------:|
+| 0.0772 | 500  | 0.0796        | -      |
+| 0.1543 | 1000 | 0.0205        | 0.6878 |
+| 0.2315 | 1500 | 0.0197        | -      |
+| 0.3087 | 2000 | 0.0201        | 0.6864 |
+| 0.3859 | 2500 | 0.0185        | -      |
+| 0.4630 | 3000 | 0.0161        | 0.6933 |
+| 0.5402 | 3500 | 0.0163        | -      |
+| 0.6174 | 4000 | 0.0172        | 0.7089 |
+| 0.6946 | 4500 | 0.0172        | -      |
+| 0.7717 | 5000 | 0.0143        | 0.7072 |
+| 0.8489 | 5500 | 0.0129        | -      |
+| 0.9261 | 6000 | 0.0124        | 0.7112 |
+| 1.0    | 6479 | -             | 0.7113 |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.2.1
+- Transformers: 4.44.2
+- PyTorch: 2.5.0+cu121
+- Accelerate: 0.34.2
+- Datasets: 3.1.0
+- 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",
+}
+```
+
+#### 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": "output/bi-encoder/qqp_cross_domain_bert-base-uncased",
+  "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 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.5.0+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 sha256:94b2b583f259ec19a4d2d7b5ba5f3e403553a2011e05b803ca99eceb95f98cb4
+size 437951328

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": 128,
+  "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": 128,
+  "model_max_length": 128,
+  "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]"
+}