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 +1,522 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:222635
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: OMBRELLAS
+  sentences:
+  - '''ALPHASORT, to sort into alphabetic order [v]'''
+  - '''OMBRELLA, an umbrella [n]'''
+  - '''PHYLLID, the leaf of a liverwort or moss [n]'''
+- source_sentence: ROUNCE
+  sentences:
+  - '''LYMPHADENITIS, inflammation of the lymph nodes [n]'''
+  - '''one who advocates curialism, the system of government of curia [n -S]'''
+  - '''part of a hand printing press [n -S]'''
+- source_sentence: SEROON
+  sentences:
+  - '''(Spanish) a crate or hamper; a bale wrapped in hide, also CEROON, SERON [n
+    -S]'''
+  - '''a white crystalline soluble phenol used as a photographic developer [n -S]'''
+  - '''serving to disseminate [adj]'''
+- source_sentence: BLAFF
+  sentences:
+  - '''to bark [v -ED, -ING, -S]'''
+  - '''RAZORCLAM, a lamellibranch mollusc with a shell like an old-fashioned razor
+    handle, also RAZORFISH [n]'''
+  - '''HYPERCORRECT, refers to a linguistic construction or pronunciation produced
+    by mistaken analogy with standard usage out of a desire to be correct, such as
+    "open widely" or "on behalf of my wife and I" [adv]'''
+- source_sentence: TRAUMATOLOGY
+  sentences:
+  - '''FELLATRIX, a female who fellates [n]'''
+  - '''pertaining to a grandparent [adj]'''
+  - '''the study of wounds and their effects [n TRAUMATOLOGIES]'''
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dictionary test
+      type: dictionary-test
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6825254231197672
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8121384167594955
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.831147364260304
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.850587516619354
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6825254231197672
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27071280558649846
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1662294728520608
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08505875166193541
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6825254231197672
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8121384167594955
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.831147364260304
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.850587516619354
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7750717041193917
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7499954655044675
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7522443165977887
+      name: Cosine Map@100
+---
+
+# 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) on the csv dataset. 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:**
+    - csv
+<!-- - **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': 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("mehularora/scrabble-embed-v2")
+# Run inference
+sentences = [
+    'TRAUMATOLOGY',
+    "'the study of wounds and their effects [n TRAUMATOLOGIES]'",
+    "'FELLATRIX, a female who fellates [n]'",
+]
+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, 0.7472, 0.0801],
+#         [0.7472, 1.0000, 0.2525],
+#         [0.0801, 0.2525, 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
+
+#### Information Retrieval
+
+* Dataset: `dictionary-test`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6825     |
+| cosine_accuracy@3   | 0.8121     |
+| cosine_accuracy@5   | 0.8311     |
+| cosine_accuracy@10  | 0.8506     |
+| cosine_precision@1  | 0.6825     |
+| cosine_precision@3  | 0.2707     |
+| cosine_precision@5  | 0.1662     |
+| cosine_precision@10 | 0.0851     |
+| cosine_recall@1     | 0.6825     |
+| cosine_recall@3     | 0.8121     |
+| cosine_recall@5     | 0.8311     |
+| cosine_recall@10    | 0.8506     |
+| **cosine_ndcg@10**  | **0.7751** |
+| cosine_mrr@10       | 0.75       |
+| cosine_map@100      | 0.7522     |
+
+<!--
+## 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
+
+#### csv
+
+* Dataset: csv
+* Size: 222,635 training samples
+* Columns: <code>word</code> and <code>definition</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | word                                                                            | definition                                                                         |
+  |:--------|:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                          | string                                                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 4.87 tokens</li><li>max: 9 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 20.32 tokens</li><li>max: 98 tokens</li></ul> |
+* Samples:
+  | word                     | definition                                                                          |
+  |:-------------------------|:------------------------------------------------------------------------------------|
+  | <code>LICHGATES</code>   | <code>'LICHGATE, the roofed gate of a churchyard, also LYCHGATE [n]'</code>         |
+  | <code>MOULDING</code>    | <code>'a long, narrow strip used to decorate a surface, also MOLDING [n -S]'</code> |
+  | <code>PARABAPTISM</code> | <code>'uncanonical baptism [n -S]'</code>                                           |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          384,
+          256
+      ],
+      "matryoshka_weights": [
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 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`: 64
+- `per_device_eval_batch_size`: 8
+- `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`: 2e-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`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `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}
+- `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`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | dictionary-test_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:------------------------------:|
+| 0.0287 | 100  | 1.0186        | 0.7180                         |
+| 0.0575 | 200  | 0.7633        | 0.7274                         |
+| 0.0862 | 300  | 0.75          | 0.7398                         |
+| 0.1150 | 400  | 0.7503        | 0.7456                         |
+| 0.1437 | 500  | 0.7271        | 0.7496                         |
+| 0.1725 | 600  | 0.6531        | 0.7508                         |
+| 0.2012 | 700  | 0.6586        | 0.7560                         |
+| 0.2300 | 800  | 0.6559        | 0.7591                         |
+| 0.2587 | 900  | 0.6116        | 0.7572                         |
+| 0.2874 | 1000 | 0.615         | 0.7625                         |
+| 0.3162 | 1100 | 0.5926        | 0.7596                         |
+| 0.3449 | 1200 | 0.6414        | 0.7623                         |
+| 0.3737 | 1300 | 0.6143        | 0.7641                         |
+| 0.4024 | 1400 | 0.6464        | 0.7655                         |
+| 0.4312 | 1500 | 0.6039        | 0.7676                         |
+| 0.4599 | 1600 | 0.514         | 0.7643                         |
+| 0.4886 | 1700 | 0.5719        | 0.7675                         |
+| 0.5174 | 1800 | 0.612         | 0.7675                         |
+| 0.5461 | 1900 | 0.5639        | 0.7698                         |
+| 0.5749 | 2000 | 0.6025        | 0.7672                         |
+| 0.6036 | 2100 | 0.5623        | 0.7719                         |
+| 0.6324 | 2200 | 0.5484        | 0.7698                         |
+| 0.6611 | 2300 | 0.5799        | 0.7730                         |
+| 0.6899 | 2400 | 0.5253        | 0.7716                         |
+| 0.7186 | 2500 | 0.5134        | 0.7732                         |
+| 0.7473 | 2600 | 0.5543        | 0.7721                         |
+| 0.7761 | 2700 | 0.5342        | 0.7736                         |
+| 0.8048 | 2800 | 0.5507        | 0.7746                         |
+| 0.8336 | 2900 | 0.5176        | 0.7737                         |
+| 0.8623 | 3000 | 0.5067        | 0.7751                         |
+| 0.8911 | 3100 | 0.548         | 0.7749                         |
+| 0.9198 | 3200 | 0.5443        | 0.7751                         |
+| 0.9485 | 3300 | 0.5603        | 0.7751                         |
+| 0.9773 | 3400 | 0.5774        | 0.7751                         |
+
+
+### Framework Versions
+- Python: 3.11.4
+- Sentence Transformers: 5.1.2
+- Transformers: 4.57.3
+- PyTorch: 2.9.1+cpu
+- Accelerate: 1.12.0
+- Datasets: 4.4.1
+- 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning},
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,25 @@
+{
+  "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": 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",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.57.3",
+    "pytorch": "2.9.1+cpu"
+  },
+  "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:a23319cbfe868af612b3053b2768054cc01ba852d461d9fb9574e7781858ed4d
+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]"
+}