Added fine-tuned transformer on parts synonyms

.gitattributes

@@ -0,0 +1,6 @@
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text

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 +1,488 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:3270
+- loss:OnlineContrastiveLoss
+- dataset_size:2044
+- dataset_size:1634
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: Door Chain
+  sentences:
+  - install new FILTER PAN COVER
+  - replace Burner Baffle
+  - install new Elbow - Fitting
+- source_sentence: install new Gasket
+  sentences:
+  - replace CIRCUIT FUSE
+  - CIRCUIT FUSE
+  - LWCO Board needs replacement
+- source_sentence: Hinge Cam
+  sentences:
+  - install new FILTER PAN COVER
+  - replace Rotary Switch
+  - Filter Dryer needs replacement
+- source_sentence: microwave
+  sentences:
+  - replace limit switch
+  - replace FILTER ENVELOPE
+  - unit
+- source_sentence: install new Actuator Switch
+  sentences:
+  - water arrestor needs replacement
+  - replace hi limit switch
+  - replace fan switch
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts b
+      type: sts-b
+    metrics:
+    - type: pearson_cosine
+      value: 0.8696194628511225
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8671637425670679
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: mtb
+      type: mtb
+    metrics:
+    - type: pearson_cosine
+      value: 0.8135998600118043
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.7237156305132463
+      name: Spearman Cosine
+---
+
+# 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 c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 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': 256, 'do_lower_case': False, 'architecture': '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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'install new Actuator Switch',
+    'replace fan switch',
+    'replace hi limit switch',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[1.0000, 0.8321, 0.8193],
+#         [0.8321, 1.0000, 0.8154],
+#         [0.8193, 0.8154, 1.0000]])
+```
+
+<!--
+### 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-b` and `mtb`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | sts-b      | mtb        |
+|:--------------------|:-----------|:-----------|
+| pearson_cosine      | 0.8696     | 0.8136     |
+| **spearman_cosine** | **0.8672** | **0.7237** |
+
+<!--
+## 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: 1,634 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                       | sentence2                                                                        | label                                           |
+  |:--------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                          | string                                                                           | int                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 4.34 tokens</li><li>max: 8 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 4.53 tokens</li><li>max: 10 tokens</li></ul> | <ul><li>0: ~18.30%</li><li>1: ~81.70%</li></ul> |
+* Samples:
+  | sentence1                    | sentence2                  | label          |
+  |:-----------------------------|:---------------------------|:---------------|
+  | <code>Expansion Valve</code> | <code>TXV Valve</code>     | <code>1</code> |
+  | <code>Drive Motor</code>     | <code>gear motor</code>    | <code>1</code> |
+  | <code>Motor Mount</code>     | <code>motor bracket</code> | <code>1</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 818 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 818 samples:
+  |         | sentence1                                                                        | sentence2                                                                        | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | int                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 5.53 tokens</li><li>max: 10 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.93 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>0: ~50.00%</li><li>1: ~50.00%</li></ul> |
+* Samples:
+  | sentence1                                  | sentence2                                   | label          |
+  |:-------------------------------------------|:--------------------------------------------|:---------------|
+  | <code>Power Relay needs replacement</code> | <code>relay needs replacement</code>        | <code>1</code> |
+  | <code>Target needs replacement</code>      | <code>ceramic tile needs replacement</code> | <code>1</code> |
+  | <code>install new Infinite Switch</code>   | <code>install new inf switch</code>         | <code>1</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
+- `learning_rate`: 1e-05
+- `num_train_epochs`: 4
+- `warmup_ratio`: 0.02
+- `bf16`: True
+- `load_best_model_at_end`: True
+
+#### 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`: 256
+- `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`: 1e-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`: 0.02
+- `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`: True
+- `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`: 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`: None
+- `hub_always_push`: False
+- `hub_revision`: None
+- `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
+- `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
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch   | Step  | Training Loss | Validation Loss | sts-b_spearman_cosine | mtb_spearman_cosine |
+|:-------:|:-----:|:-------------:|:---------------:|:---------------------:|:-------------------:|
+| -1      | -1    | -             | -               | 0.8672                | 0.7237              |
+| 1.0     | 7     | -             | 28.7758         | -                     | -                   |
+| 2.0     | 14    | -             | 20.5461         | -                     | -                   |
+| 3.0     | 21    | -             | 14.5468         | -                     | -                   |
+| 4.0     | 28    | -             | 12.2789         | -                     | -                   |
+| 5.0     | 35    | -             | 7.4563          | -                     | -                   |
+| 6.0     | 42    | -             | 4.7709          | -                     | -                   |
+| 7.0     | 49    | -             | 3.7263          | -                     | -                   |
+| 8.0     | 56    | -             | 3.2799          | -                     | -                   |
+| 9.0     | 63    | -             | 3.4937          | -                     | -                   |
+| 10.0    | 70    | -             | 3.3956          | -                     | -                   |
+| 11.0    | 77    | -             | 3.2518          | -                     | -                   |
+| 12.0    | 84    | -             | 2.4912          | -                     | -                   |
+| 13.0    | 91    | -             | 1.7859          | -                     | -                   |
+| 14.0    | 98    | -             | 1.4185          | -                     | -                   |
+| 14.2857 | 100   | 9.9923        | -               | -                     | -                   |
+| 15.0    | 105   | -             | 1.4582          | -                     | -                   |
+| 16.0    | 112   | -             | 1.4355          | -                     | -                   |
+| 17.0    | 119   | -             | 1.2700          | -                     | -                   |
+| 18.0    | 126   | -             | 0.9766          | -                     | -                   |
+| 19.0    | 133   | -             | 0.9087          | -                     | -                   |
+| 20.0    | 140   | -             | 0.8227          | -                     | -                   |
+| 21.0    | 147   | -             | 0.7897          | -                     | -                   |
+| 22.0    | 154   | -             | 0.6956          | -                     | -                   |
+| 23.0    | 161   | -             | 0.7913          | -                     | -                   |
+| 24.0    | 168   | -             | 0.7902          | -                     | -                   |
+| 25.0    | 175   | -             | 0.7534          | -                     | -                   |
+| 26.0    | 182   | -             | 0.6562          | -                     | -                   |
+| 27.0    | 189   | -             | 0.5444          | -                     | -                   |
+| 28.0    | 196   | -             | 0.4464          | -                     | -                   |
+| 28.5714 | 200   | 0.2576        | -               | -                     | -                   |
+| 29.0    | 203   | -             | 0.4410          | -                     | -                   |
+| 30.0    | 210   | -             | 0.4314          | -                     | -                   |
+| 31.0    | 217   | -             | 0.3471          | -                     | -                   |
+| 32.0    | 224   | -             | 0.3472          | -                     | -                   |
+| 33.0    | 231   | -             | 0.3445          | -                     | -                   |
+| 34.0    | 238   | -             | 0.3404          | -                     | -                   |
+| 35.0    | 245   | -             | 0.3378          | -                     | -                   |
+| 36.0    | 252   | -             | 0.3370          | -                     | -                   |
+| 37.0    | 259   | -             | 0.3355          | -                     | -                   |
+| 38.0    | 266   | -             | 0.3339          | -                     | -                   |
+| 39.0    | 273   | -             | 0.3326          | -                     | -                   |
+| 40.0    | 280   | -             | 0.3328          | -                     | -                   |
+| 41.0    | 287   | -             | 0.3308          | -                     | -                   |
+| 42.0    | 294   | -             | 0.3308          | -                     | -                   |
+| 42.8571 | 300   | 0.1918        | -               | -                     | -                   |
+| 43.0    | 301   | -             | 0.3306          | -                     | -                   |
+| 44.0    | 308   | -             | 0.3304          | -                     | -                   |
+| 45.0    | 315   | -             | 0.3294          | -                     | -                   |
+| 46.0    | 322   | -             | 0.3295          | -                     | -                   |
+| 47.0    | 329   | -             | 0.3295          | -                     | -                   |
+| 48.0    | 336   | -             | 0.3297          | -                     | -                   |
+| 49.0    | 343   | -             | 0.3295          | -                     | -                   |
+| 50.0    | 350   | -             | 0.3295          | -                     | -                   |
+| **1.0** | **4** | **-**         | **0.191**       | **-**                 | **-**               |
+| 2.0     | 8     | -             | 0.1209          | -                     | -                   |
+| 3.0     | 12    | -             | 0.1106          | -                     | -                   |
+| 4.0     | 16    | -             | 0.1035          | -                     | -                   |
+| 5.0     | 20    | -             | 0.0995          | -                     | -                   |
+| 6.0     | 24    | -             | 0.0955          | -                     | -                   |
+| 7.0     | 28    | -             | 0.0587          | -                     | -                   |
+| 8.0     | 32    | -             | 0.0574          | -                     | -                   |
+| 9.0     | 36    | -             | 0.0             | -                     | -                   |
+| 10.0    | 40    | -             | 0.0             | -                     | -                   |
+| 11.0    | 44    | -             | 0.0             | -                     | -                   |
+| 12.0    | 48    | -             | 0.0             | -                     | -                   |
+| 12.5    | 50    | 0.4241        | -               | -                     | -                   |
+| 13.0    | 52    | -             | 0.0             | -                     | -                   |
+| 14.0    | 56    | -             | 0.0             | -                     | -                   |
+| 15.0    | 60    | -             | 0.0             | -                     | -                   |
+| 1.0     | 7     | -             | 0.0684          | -                     | -                   |
+| 2.0     | 14    | -             | 0.0             | -                     | -                   |
+| 3.0     | 21    | -             | 0.0             | -                     | -                   |
+| 4.0     | 28    | -             | 0.0             | -                     | -                   |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.0rc1
+- Sentence Transformers: 5.0.0
+- Transformers: 4.53.1
+- PyTorch: 2.7.1+cu126
+- Accelerate: 1.8.1
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
+
+## 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 +1,25 @@
+{
+  "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": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.0.0",
+    "transformers": "4.53.1",
+    "pytorch": "2.7.1+cu126"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a52cfa870a7dedfe8643c3c865eb246fff12618fd2a57aee453da84c452171
+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 +1,65 @@
+{
+  "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
+    },
+    "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": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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]"
+}