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 +1,514 @@
+---
+base_model: pritamdeka/assamese-bert-nli-v2
+datasets:
+- sentence-transformers/stsb
+language:
+- en
+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:5749
+- loss:CosineSimilarityLoss
+widget:
+- source_sentence: The man talked to a girl over the internet camera.
+  sentences:
+  - A group of elderly people pose around a dining table.
+  - A teenager talks to a girl over a webcam.
+  - There is no 'still' that is not relative to some other object.
+- source_sentence: A woman is writing something.
+  sentences:
+  - Two eagles are perched on a branch.
+  - It refers to the maximum f-stop (which is defined as the ratio of focal length
+    to effective aperture diameter).
+  - A woman is chopping green onions.
+- source_sentence: The player shoots the winning points.
+  sentences:
+  - Minimum wage laws hurt the least skilled, least productive the most.
+  - The basketball player is about to score points for his team.
+  - Sheep are grazing in the field in front of a line of trees.
+- source_sentence: Stars form in star-formation regions, which itself develop from
+    molecular clouds.
+  sentences:
+  - Although I believe Searle is mistaken, I don't think you have found the problem.
+  - It may be possible for a solar system like ours to exist outside of a galaxy.
+  - A blond-haired child performing on the trumpet in front of a house while his younger
+    brother watches.
+- source_sentence: While Queen may refer to both Queen regent (sovereign) or Queen
+    consort, the King has always been the sovereign.
+  sentences:
+  - At first, I thought this is a bit of a tricky question.
+  - A man sitting on the floor in a room is strumming a guitar.
+  - There is a very good reason not to refer to the Queen's spouse as "King" - because
+    they aren't the King.
+model-index:
+- name: SentenceTransformer based on pritamdeka/assamese-bert-nli-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.8768922454773975
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8768666342138283
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8644469622686086
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8707690120902617
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8653235671487655
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8718775857334757
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8524585875711483
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8517262744664453
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8768922454773975
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8768666342138283
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.8527208821672074
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8555556328238375
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8490059674398979
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8513628040355813
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8488820547009427
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8514695594991134
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8179930227975002
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8197337942826736
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8527208821672074
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8555556328238375
+      name: Spearman Max
+---
+
+# SentenceTransformer based on pritamdeka/assamese-bert-nli-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [pritamdeka/assamese-bert-nli-v2](https://huggingface.co/pritamdeka/assamese-bert-nli-v2) on the [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) dataset. 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:** [pritamdeka/assamese-bert-nli-v2](https://huggingface.co/pritamdeka/assamese-bert-nli-v2) <!-- at revision 1f2c1246128304aed5ae3fd6ab1b2b4be69462f2 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': 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("pritamdeka/assamese-bert-nli-v2-sts")
+# Run inference
+sentences = [
+    'While Queen may refer to both Queen regent (sovereign) or Queen consort, the King has always been the sovereign.',
+    'There is a very good reason not to refer to the Queen\'s spouse as "King" - because they aren\'t the King.',
+    'A man sitting on the floor in a room is strumming a guitar.',
+]
+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
+
+#### Semantic Similarity
+* Dataset: `sts-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8769     |
+| **spearman_cosine** | **0.8769** |
+| pearson_manhattan   | 0.8644     |
+| spearman_manhattan  | 0.8708     |
+| pearson_euclidean   | 0.8653     |
+| spearman_euclidean  | 0.8719     |
+| pearson_dot         | 0.8525     |
+| spearman_dot        | 0.8517     |
+| pearson_max         | 0.8769     |
+| spearman_max        | 0.8769     |
+
+#### Semantic Similarity
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8527     |
+| **spearman_cosine** | **0.8556** |
+| pearson_manhattan   | 0.849      |
+| spearman_manhattan  | 0.8514     |
+| pearson_euclidean   | 0.8489     |
+| spearman_euclidean  | 0.8515     |
+| pearson_dot         | 0.818      |
+| spearman_dot        | 0.8197     |
+| pearson_max         | 0.8527     |
+| spearman_max        | 0.8556     |
+
+<!--
+## 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
+
+#### sentence-transformers/stsb
+
+* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
+* Size: 5,749 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: 6 tokens</li><li>mean: 10.26 tokens</li><li>max: 28 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 10.23 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                  | sentence2                                                             | score             |
+  |:-----------------------------------------------------------|:----------------------------------------------------------------------|:------------------|
+  | <code>A plane is taking off.</code>                        | <code>An air plane is taking off.</code>                              | <code>1.0</code>  |
+  | <code>A man is playing a large flute.</code>               | <code>A man is playing a flute.</code>                                | <code>0.76</code> |
+  | <code>A man is spreading shreded cheese on a pizza.</code> | <code>A man is spreading shredded cheese on an uncooked pizza.</code> | <code>0.76</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### sentence-transformers/stsb
+
+* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
+* Size: 1,500 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: 5 tokens</li><li>mean: 15.4 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.41 tokens</li><li>max: 43 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.47</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                         | sentence2                                             | score             |
+  |:--------------------------------------------------|:------------------------------------------------------|:------------------|
+  | <code>A man with a hard hat is dancing.</code>    | <code>A man wearing a hard hat is dancing.</code>     | <code>1.0</code>  |
+  | <code>A young child is riding a horse.</code>     | <code>A child is riding a horse.</code>               | <code>0.95</code> |
+  | <code>A man is feeding a mouse to a snake.</code> | <code>The man is feeding a mouse to the snake.</code> | <code>1.0</code>  |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 4
+- `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`: 4
+- `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 | Training Loss | loss   | sts-dev_spearman_cosine | sts-test_spearman_cosine |
+|:------:|:----:|:-------------:|:------:|:-----------------------:|:------------------------:|
+| 0.2778 | 100  | 0.026         | 0.0236 | 0.8757                  | -                        |
+| 0.5556 | 200  | 0.0259        | 0.0262 | 0.8612                  | -                        |
+| 0.8333 | 300  | 0.0238        | 0.0232 | 0.8729                  | -                        |
+| 1.1111 | 400  | 0.0191        | 0.0248 | 0.8718                  | -                        |
+| 1.3889 | 500  | 0.0117        | 0.0236 | 0.8729                  | -                        |
+| 1.6667 | 600  | 0.011         | 0.0233 | 0.8728                  | -                        |
+| 1.9444 | 700  | 0.0114        | 0.0238 | 0.8757                  | -                        |
+| 2.2222 | 800  | 0.0076        | 0.0231 | 0.8760                  | -                        |
+| 2.5    | 900  | 0.0058        | 0.0230 | 0.8756                  | -                        |
+| 2.7778 | 1000 | 0.0055        | 0.0229 | 0.8760                  | -                        |
+| 3.0556 | 1100 | 0.006         | 0.0225 | 0.8776                  | -                        |
+| 3.3333 | 1200 | 0.0039        | 0.0227 | 0.8761                  | -                        |
+| 3.6111 | 1300 | 0.004         | 0.0228 | 0.8761                  | -                        |
+| 3.8889 | 1400 | 0.0039        | 0.0227 | 0.8769                  | -                        |
+| 4.0    | 1440 | -             | -      | -                       | 0.8556                   |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.4
+- PyTorch: 2.3.1+cu121
+- Accelerate: 0.32.1
+- Datasets: 2.20.0
+- 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",
+}
+```
+
+<!--
+## 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": "pritamdeka/assamese-bert-nli-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 197285
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.4",
+    "pytorch": "2.3.1+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:b2cc3c9393805f9f2737542e55077597591b4f64f8e216b0074d239c8693531d
+size 950247272

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 +1,65 @@
+{
+  "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
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "[SEP]",
+      "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": false,
+  "lowercase": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "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": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}