Upload folder using huggingface_hub

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 +1,468 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:44114
+- loss:ContrastiveLoss
+widget:
+- source_sentence: The city is located in 1889 , along the Nehalem River and Nehalem
+    Bay , near the Pacific Ocean .
+  sentences:
+  - Incorporated in 1889 , the city lies along the Pacific Ocean near the Nehalem
+    River and Nehalem Bay .
+  - Along the coast there are almost 2,000 islands , about three quarters of which
+    are uninhabited .
+  - The mammalian fauna of Madagascar is largely endemic and highly distinctive .
+- source_sentence: Chris Blackwell , the mother of Blackwell , was one of the greatest
+    landowners in Saint Mary at the turn of the 20th century .
+  sentences:
+  - One of the largest landowners in Saint Mary at the turn of the twentieth century
+    was Blanche Blackwell , mother of Chris Blackwell .
+  - The cast for the third season of `` California Dreams '' was the same as the cast
+    for the fourth season .
+  - 'The affine scaling direction can be used to define a heuristic to adaptively
+    the centering parameter as :'
+- source_sentence: The Roman - Catholic diocese of Cyangugu is a diocese in the city
+    of Cyangugu in the church province of Kigali , Rwanda .
+  sentences:
+  - Chad Ochocinco ( born 1978 ; formerly Chad Johnson ) is an American - American
+    - football receiver .
+  - She published several jingles and sang some successful music videos .
+  - The Roman Catholic Diocese of Cyangugu is a diocese located in the city of Kigali
+    in the ecclesiastical province of Cyangugu in Rwanda .
+- source_sentence: Abhishek introduces Rishi and Netra Tanuja as his wife .
+  sentences:
+  - Abhishek introduces Tanuja to Rishi and Netra as his wife .
+  - At the end of the 18th century the castle was property of the Counts Ansidei ,
+    in the 19th century it was bought by the Piceller family .
+  - Deepaaradhana is an Indian Malayalam film of 1983 , produced by Vijayanand and
+    directed by TK Balachandran .
+- source_sentence: He is also well singing in other regional forms such as Bhajans
+    , Ghazals , Nazrulgeeti and numerous semi-classical songs .
+  sentences:
+  - When the membrane potential reaches approximately – 60 mV , the K channels close
+    and the Na channels open and the prepotential phase begins again .
+  - He is also skilled in singing other regional forms like Bhajans , Ghazals , Nazrulgeeti
+    and numerous semi-classical songs as well .
+  - Conotalopia mustelina is a species of sea snail , a top gastropod mollusk in the
+    Trochidae family , the navy snails .
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- cosine_mcc
+model-index:
+- name: SentenceTransformer
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: paws val watcher
+      type: paws-val-watcher
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9277327935222672
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.8190367221832275
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9206490331184708
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.8180307745933533
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.8942141623488774
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9486944571690334
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9612681828396534
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.8556704322534656
+      name: Cosine Mcc
+---
+
+# SentenceTransformer
+
+This is a [sentence-transformers](https://www.SBERT.net) model trained. 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:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 64 tokens
+- **Output Dimensionality:** 768 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/huggingface/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': 64, 'do_lower_case': False, 'architecture': '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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'He is also well singing in other regional forms such as Bhajans , Ghazals , Nazrulgeeti and numerous semi-classical songs .',
+    'He is also skilled in singing other regional forms like Bhajans , Ghazals , Nazrulgeeti and numerous semi-classical songs as well .',
+    'Conotalopia mustelina is a species of sea snail , a top gastropod mollusk in the Trochidae family , the navy snails .',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[1.0000, 0.9958, 0.5938],
+#         [0.9958, 1.0000, 0.6041],
+#         [0.5938, 0.6041, 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
+
+#### Binary Classification
+
+* Dataset: `paws-val-watcher`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                    | Value      |
+|:--------------------------|:-----------|
+| cosine_accuracy           | 0.9277     |
+| cosine_accuracy_threshold | 0.819      |
+| cosine_f1                 | 0.9206     |
+| cosine_f1_threshold       | 0.818      |
+| cosine_precision          | 0.8942     |
+| cosine_recall             | 0.9487     |
+| **cosine_ap**             | **0.9613** |
+| cosine_mcc                | 0.8557     |
+
+<!--
+## 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: 44,114 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                                                                             | float                                                          |
+  | details | <ul><li>min: 12 tokens</li><li>mean: 26.76 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 26.82 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.49</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                 | sentence_1                                                                                                                                                                    | label            |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>The southern area contains the Tara Mountains and the northern area consists of open plains along the coast , and the city proper .</code>                           | <code>The southern area contains the Tara mountains and the northern area consists of open plains along the coast and the actual city .</code>                                | <code>1.0</code> |
+  | <code>It began as a fishing village inhabited by Polish settlers from the Kaszub region in 1870 , as well as by some German immigrants .</code>                            | <code>It began as a fishing village populated by German settlers from the Kaszub region , as well as some Polish immigrants in 1870 .</code>                                  | <code>0.0</code> |
+  | <code>Wyoming Highway 377 was a short Wyoming state road in central Sweetwater County that served the community of Point of Rocks and the Jim Bridger Power Plant .</code> | <code>Wyoming Highway 377 was a short Wyoming State Road in central Sweetwater County that served as the community of Point of Rocks and the Jim Bridger Power Plant .</code> | <code>1.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 4
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: no
+- `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`: 4
+- `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
+- `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}
+- `parallelism_config`: None
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `project`: huggingface
+- `trackio_space_id`: trackio
+- `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`: no
+- `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`: True
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step  | Training Loss | paws-val-watcher_cosine_ap |
+|:------:|:-----:|:-------------:|:--------------------------:|
+| 0.1813 | 500   | 0.0319        | -                          |
+| 0.3626 | 1000  | 0.0224        | -                          |
+| 0.5439 | 1500  | 0.0175        | -                          |
+| 0.7252 | 2000  | 0.0146        | -                          |
+| 0.9065 | 2500  | 0.013         | -                          |
+| 1.0    | 2758  | -             | 0.9348                     |
+| 1.0877 | 3000  | 0.0109        | -                          |
+| 1.2690 | 3500  | 0.0092        | -                          |
+| 1.4503 | 4000  | 0.0085        | -                          |
+| 1.6316 | 4500  | 0.008         | -                          |
+| 1.8129 | 5000  | 0.0075        | -                          |
+| 1.9942 | 5500  | 0.0076        | -                          |
+| 2.0    | 5516  | -             | 0.9543                     |
+| 2.1755 | 6000  | 0.0053        | -                          |
+| 2.3568 | 6500  | 0.0053        | -                          |
+| 2.5381 | 7000  | 0.0052        | -                          |
+| 2.7194 | 7500  | 0.0049        | -                          |
+| 2.9007 | 8000  | 0.0047        | -                          |
+| 3.0    | 8274  | -             | 0.9580                     |
+| 3.0819 | 8500  | 0.0042        | -                          |
+| 3.2632 | 9000  | 0.0037        | -                          |
+| 3.4445 | 9500  | 0.0035        | -                          |
+| 3.6258 | 10000 | 0.0036        | -                          |
+| 3.8071 | 10500 | 0.0036        | -                          |
+| 3.9884 | 11000 | 0.0036        | -                          |
+| 4.0    | 11032 | -             | 0.9613                     |
+
+
+### Framework Versions
+- Python: 3.12.12
+- Sentence Transformers: 5.2.0
+- Transformers: 4.57.3
+- PyTorch: 2.9.0+cu126
+- Accelerate: 1.12.0
+- Datasets: 4.0.0
+- Tokenizers: 0.22.1
+
+## 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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,
+  "dtype": "float32",
+  "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",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.2.0",
+    "transformers": "4.57.3",
+    "pytorch": "2.9.0+cu126"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

eval/binary_classification_evaluation_paws-val-watcher_results.csv

@@ -0,0 +1,5 @@
+epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision,cosine_recall,cosine_f1_threshold,cosine_ap,cosine_mcc
+1.0,2758,0.8921052631578947,0.8806893504197968,0.8506188647033718,0.912963811268896,0.9348496837429896,0.7817241689872801
+2.0,5516,0.9172064777327935,0.9061946902654867,0.8763371844244758,0.9381584974805314,0.9543142650820976,0.8288923423316907
+3.0,8274,0.9257085020242914,0.9172118204376268,0.9035555555555556,0.9312872194228127,0.9580228650892402,0.8501826095361721
+4.0,11032,0.9277327935222672,0.9206490331184708,0.8942141623488774,0.9486944571690334,0.9612681828396534,0.8556704322534656

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9703cfb86d37815e801f54ef9122246d0630215514ae90e3b1cdf1d590412c34
+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": 64,
+    "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 +1,63 @@
+{
+  "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_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 64,
+  "model_max_length": 64,
+  "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]"
+}