Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,494 @@
+---
+language: []
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:10K<n<100K
+- loss:CoSENTLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: Driving or commuting to work feels draining, even if it's a short
+    distance.
+  sentences:
+  - Symptoms during a manic episode include decreased need for sleep, more talkative
+    than usual, flight of ideas, distractibility
+  - I feel like I have lost a part of myself since the traumatic event, and I struggle
+    to connect with others on a deeper level.
+  - For at least 2 years, or 1 year in children and adolescents, numerous periods
+    with hypomanic symptoms and depressive symptoms occur, neither meeting full criteria
+    for hypomanic or major depressive episodes.
+- source_sentence: I felt like my thoughts were disconnected and chaotic during a
+    manic episode.
+  sentences:
+  - Diagnosis requires one or more manic episodes, which may be preceded or followed
+    by hypomanic or major depressive episodes.
+  - I feel like I have lost a part of myself since the traumatic event, and I struggle
+    to connect with others on a deeper level.
+  - Depressed mood for most of the day, for more days than not, as indicated by subjective
+    account or observation, for at least 2 years.
+- source_sentence: My insomnia has caused me to experience frequent headaches and
+    muscle soreness.
+  sentences:
+  - Insomnia or hypersomnia nearly every day.
+  - I have difficulty standing in long lines at the grocery store or the bank due
+    to the fear of feeling trapped or overwhelmed.
+  - For at least 2 years, or 1 year in children and adolescents, numerous periods
+    with hypomanic symptoms and depressive symptoms occur, neither meeting full criteria
+    for hypomanic or major depressive episodes.
+- source_sentence: The phobic object or situation almost always provokes immediate
+    fear or anxiety.
+  sentences:
+  - The agoraphobic situations almost always provoke fear or anxiety.
+  - I have difficulty standing in long lines at the grocery store or the bank due
+    to the fear of feeling trapped or overwhelmed.
+  - For at least 2 years, or 1 year in children and adolescents, numerous periods
+    with hypomanic symptoms and depressive symptoms occur, neither meeting full criteria
+    for hypomanic or major depressive episodes.
+- source_sentence: I engage in risky behaviors like reckless driving or reckless sexual
+    encounters.
+  sentences:
+  - Symptoms during a manic episode include inflated self-esteem or grandiosity,increased
+    goal-directed activity, or excessive involvement in risky activities.
+  - Marked decrease in functioning in areas like work, interpersonal relations, or
+    self-care since the onset of the disturbance.
+  - The agoraphobic situations are actively avoided, require the presence of a companion,
+    or are endured with intense fear or anxiety.
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: FT label
+      type: FT_label
+    metrics:
+    - type: pearson_cosine
+      value: 0.40571243927086686
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.4157655660967662
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.4294377953337607
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.41636474785618866
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.4293067637823527
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.41576593946890283
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.4057124337715868
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.4157663124606592
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.4294377953337607
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.41636474785618866
+      name: Spearman Max
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision e4ce9877abf3edfe10b0d82785e83bdcb973e22e -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("Hgkang00/FT-label-consent-10")
+# Run inference
+sentences = [
+    'I engage in risky behaviors like reckless driving or reckless sexual encounters.',
+    'Symptoms during a manic episode include inflated self-esteem or grandiosity,increased goal-directed activity, or excessive involvement in risky activities.',
+    'Marked decrease in functioning in areas like work, interpersonal relations, or self-care since the onset of the disturbance.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+* Dataset: `FT_label`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.4057     |
+| **spearman_cosine** | **0.4158** |
+| pearson_manhattan   | 0.4294     |
+| spearman_manhattan  | 0.4164     |
+| pearson_euclidean   | 0.4293     |
+| spearman_euclidean  | 0.4158     |
+| pearson_dot         | 0.4057     |
+| spearman_dot        | 0.4158     |
+| pearson_max         | 0.4294     |
+| spearman_max        | 0.4164     |
+
+<!--
+## 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: 33,800 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: 29 tokens</li><li>mean: 29.0 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 25.15 tokens</li><li>max: 43 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.06</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                                                                            | sentence2                                                                                                                                 | score            |
+  |:-------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>Presence of delusions, hallucinations or disorganized speech, for a significant portion of time within a 1-month period</code> | <code>I often hear voices telling me things that are not real, even when I'm alone in my room.</code>                                     | <code>1.0</code> |
+  | <code>Presence of delusions, hallucinations or disorganized speech, for a significant portion of time within a 1-month period</code> | <code>I have strong beliefs that people are plotting against me and trying to harm me, which makes it hard for me to trust anyone.</code> | <code>1.0</code> |
+  | <code>Presence of delusions, hallucinations or disorganized speech, for a significant portion of time within a 1-month period</code> | <code>Sometimes, I see things that others around me don't see, like strange figures or objects.</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"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 4,225 evaluation 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: 18 tokens</li><li>mean: 31.8 tokens</li><li>max: 60 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 24.59 tokens</li><li>max: 41 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.06</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                                                                            | sentence2                                                                                                                         | score            |
+  |:-------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>Presence of delusions, hallucinations or disorganized speech, for a significant portion of time within a 1-month period</code> | <code>People around me have noticed that my behavior is becoming more erratic and unpredictable.</code>                           | <code>1.0</code> |
+  | <code>Presence of delusions, hallucinations or disorganized speech, for a significant portion of time within a 1-month period</code> | <code>There are times when I repeat certain actions or words without any clear purpose, almost like being stuck in a loop.</code> | <code>0.0</code> |
+  | <code>Presence of delusions, hallucinations or disorganized speech, for a significant portion of time within a 1-month period</code> | <code>I feel detached from reality at times and have trouble distinguishing between what is real and what is not.</code>          | <code>0.0</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`: epoch
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 128
+- `num_train_epochs`: 10
+- `warmup_ratio`: 0.1
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 128
+- `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`: 10
+- `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`: 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
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss    | FT_label_spearman_cosine |
+|:------:|:----:|:-------------:|:-------:|:------------------------:|
+| 0.0377 | 10   | 11.8816       | -       | -                        |
+| 0.0755 | 20   | 12.0633       | -       | -                        |
+| 0.1132 | 30   | 11.2972       | -       | -                        |
+| 0.1509 | 40   | 11.4435       | -       | -                        |
+| 0.1887 | 50   | 10.9872       | -       | -                        |
+| 0.2264 | 60   | 10.3121       | -       | -                        |
+| 0.2642 | 70   | 10.0711       | -       | -                        |
+| 0.3019 | 80   | 9.6888        | -       | -                        |
+| 0.3396 | 90   | 9.2037        | -       | -                        |
+| 0.3774 | 100  | 8.6158        | -       | -                        |
+| 0.4151 | 110  | 8.4605        | -       | -                        |
+| 0.4528 | 120  | 8.202         | -       | -                        |
+| 0.4906 | 130  | 7.9642        | -       | -                        |
+| 0.5283 | 140  | 7.8384        | -       | -                        |
+| 0.5660 | 150  | 7.8803        | -       | -                        |
+| 0.6038 | 160  | 7.419         | -       | -                        |
+| 1.0    | 133  | 8.435         | 8.1138  | 0.3813                   |
+| 2.0    | 266  | 7.7886        | 8.2494  | 0.4003                   |
+| 3.0    | 399  | 7.164         | 8.7060  | 0.4048                   |
+| 4.0    | 532  | 6.5921        | 9.5854  | 0.3882                   |
+| 5.0    | 665  | 6.2349        | 10.5716 | 0.4042                   |
+| 6.0    | 798  | 5.7831        | 10.9500 | 0.4147                   |
+| 7.0    | 931  | 5.4894        | 11.6387 | 0.4120                   |
+| 8.0    | 1064 | 5.2348        | 12.2129 | 0.4113                   |
+| 9.0    | 1197 | 5.0118        | 12.4632 | 0.4099                   |
+| 10.0   | 1330 | 4.8566        | 12.7203 | 0.4158                   |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.1
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.30.1
+- Datasets: 2.19.1
+- 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 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.6.1",
+    "pytorch": "1.8.1"
+  },
+  "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:f3a525b23b32a428d95f74868eeea2040b38627ba68a795e6cdc9a1fd81b329b
+size 90864192

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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]",
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}