Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unigram.json 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 +1,540 @@
+---
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+datasets: []
+language: []
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- manhattan_accuracy
+- manhattan_accuracy_threshold
+- manhattan_f1
+- manhattan_f1_threshold
+- manhattan_precision
+- manhattan_recall
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_accuracy_threshold
+- euclidean_f1
+- euclidean_f1_threshold
+- euclidean_precision
+- euclidean_recall
+- euclidean_ap
+- max_accuracy
+- max_accuracy_threshold
+- max_f1
+- max_f1_threshold
+- max_precision
+- max_recall
+- max_ap
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:410745
+- loss:ContrastiveLoss
+widget:
+- source_sentence: وینچ
+  sentences:
+  - ترقه شکلاتی ( هفت ترقه ) ناریه پارس درجه 1 بسته 15 عددی ترقه شکلاتی ( هفت ترقه
+    ) ناریه پارس درجه 1 بسته 15 عددی 10عدد ناریه ترقه شکلاتی هفت ترقه بار تازه بدون
+    رطوبت وخرابی مارک معتبر نورافشانی
+  - پارچه میکرو کجراه
+  - Car winch-1500LBS-KARA وینچ خودرو آفرود ۶۸۰ کیلوگرم کارا ۱۵۰۰lbs وینچ خودرویی
+    (جلو ماشینی) 1500LBS کارا (KARA)
+- source_sentence: ' وسپا '
+  sentences:
+  - پولوشرت زرد وسپا
+  - دوچرخه بند سقفی  لیفان X70 ایکس 70 آلومینیومی طرح منابو
+  - دوچرخه ویوا Oxygen سایز 26 دوچرخه 26 ويوا OXYGEN دوچرخه کوهستان ویوا مدل OXYGEN
+    سایز 26
+- source_sentence: دوچرخه المپیا سایز 27 5
+  sentences:
+  - دوچرخه شهری المپیا کد 16220 سایز 16 دوچرخه شهری المپیا کد 16220 سایز 16 دوچرخه
+    المپیا کد 16220 سایز 16 - OLYMPIA
+  - لامپ اس ام دی خودرو مدل 8B بسته 2 عددی
+  - قیمت کمپرس سنج موتور
+- source_sentence: دچرخه ی
+  sentences:
+  - هیدروفیشیال ۷ کاره نیوفیس پلاس متور سنگین ۲۰۲۲
+  - جامدادی کیوت
+  - جعبه ی کادو ی رنگی
+- source_sentence: هایومکس
+  sentences:
+  - انگشتر حدید صینی کد2439
+  - ژل هایومکس ولومایزر 2 سی سی
+  - دزدگیر پاناتک مدل P-CA501 دزدگیر پاناتک P-CA501-2 دزدگیر پاناتک مدل P-CA501-2
+model-index:
+- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy
+      value: 0.8531738206358597
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.763870358467102
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9032999224561303
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7447167634963989
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.8649689236015621
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9451857194374323
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9354580013152192
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.8179627073336401
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 17.24372100830078
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.8831898479427548
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 16.905807495117188
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.8255042324171805
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9495432143286453
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.9192801272426158
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.8484629374000306
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 56.168235778808594
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.9006901291486498
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 57.448089599609375
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.8601706503309084
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.9452157711263373
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.9331690796886208
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.8485944039089375
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 3.5569825172424316
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.9009756516265629
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 3.694398880004883
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.8597717468465025
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.9463276836158192
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.9332275611001725
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.8531738206358597
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 56.168235778808594
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.9032999224561303
+      name: Max F1
+    - type: max_f1_threshold
+      value: 57.448089599609375
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.8649689236015621
+      name: Max Precision
+    - type: max_recall
+      value: 0.9495432143286453
+      name: Max Recall
+    - type: max_ap
+      value: 0.9354580013152192
+      name: Max Ap
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-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/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision bf3bf13ab40c3157080a7ab344c831b9ad18b5eb -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## 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("DashReza7/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2_FINETUNED_on_torob_data_v5")
+# Run inference
+sentences = [
+    'هایومکس',
+    'ژل هایومکس ولومایزر 2 سی سی',
+    'دزدگیر پاناتک مدل P-CA501 دزدگیر پاناتک P-CA501-2 دزدگیر پاناتک مدل P-CA501-2',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Binary Classification
+
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.8532     |
+| cosine_accuracy_threshold    | 0.7639     |
+| cosine_f1                    | 0.9033     |
+| cosine_f1_threshold          | 0.7447     |
+| cosine_precision             | 0.865      |
+| cosine_recall                | 0.9452     |
+| cosine_ap                    | 0.9355     |
+| dot_accuracy                 | 0.818      |
+| dot_accuracy_threshold       | 17.2437    |
+| dot_f1                       | 0.8832     |
+| dot_f1_threshold             | 16.9058    |
+| dot_precision                | 0.8255     |
+| dot_recall                   | 0.9495     |
+| dot_ap                       | 0.9193     |
+| manhattan_accuracy           | 0.8485     |
+| manhattan_accuracy_threshold | 56.1682    |
+| manhattan_f1                 | 0.9007     |
+| manhattan_f1_threshold       | 57.4481    |
+| manhattan_precision          | 0.8602     |
+| manhattan_recall             | 0.9452     |
+| manhattan_ap                 | 0.9332     |
+| euclidean_accuracy           | 0.8486     |
+| euclidean_accuracy_threshold | 3.557      |
+| euclidean_f1                 | 0.901      |
+| euclidean_f1_threshold       | 3.6944     |
+| euclidean_precision          | 0.8598     |
+| euclidean_recall             | 0.9463     |
+| euclidean_ap                 | 0.9332     |
+| max_accuracy                 | 0.8532     |
+| max_accuracy_threshold       | 56.1682    |
+| max_f1                       | 0.9033     |
+| max_f1_threshold             | 57.4481    |
+| max_precision                | 0.865      |
+| max_recall                   | 0.9495     |
+| **max_ap**                   | **0.9355** |
+
+<!--
+## 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 Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 2
+- `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`: 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
+- `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`: 2
+- `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 | max_ap |
+|:------:|:----:|:-------------:|:------:|
+| None   | 0    | -             | 0.8131 |
+| 0.3115 | 500  | 0.0256        | -      |
+| 0.6231 | 1000 | 0.0179        | -      |
+| 0.9346 | 1500 | 0.0165        | -      |
+| 1.2461 | 2000 | 0.0152        | -      |
+| 1.5576 | 2500 | 0.0148        | -      |
+| 1.8692 | 3000 | 0.0144        | -      |
+| 2.0    | 3210 | -             | 0.9355 |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.4
+- PyTorch: 2.4.0+cu121
+- Accelerate: 0.32.1
+- Datasets: 2.21.0
+- 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",
+}
+```
+
+#### 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 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 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": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.4",
+    "pytorch": "2.4.0+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:bea1729e8232abb0d1fa1f6312b739a8d711893b3780e11b7df328518c42dfef
+size 470637416

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": 128,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260