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 +1,497 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:68828
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: Men is de toegangssleutels verloren
+  sentences:
+  - De centrale verwarming
+  - niet dringend
+  - Weg
+- source_sentence: De bovenste constructie
+  sentences:
+  - Voldoende warm water in de hele woning
+  - daklekkage
+  - lek in kraan
+- source_sentence: De box in het souterrain
+  sentences:
+  - Vloer
+  - lift niet
+  - Nood uitgang
+- source_sentence: balkon
+  sentences:
+  - de brievenbus
+  - uitgang garage dicht
+  - afvoer de douche
+- source_sentence: De deur naar de kelderboxen is stuk
+  sentences:
+  - deur met dranger
+  - De beugel om de plek vrij te houden
+  - kelderboxen deur
+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 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: 0.982086820083682
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.733125627040863
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9821498371335505
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.733125627040863
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9787068293949623
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9856171548117155
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9972864020390366
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.964197674565882
+      name: Cosine Mcc
+---
+
+# 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 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 64 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': 64, '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("PrabalAryal/Sentence_Transformer_v0.0.4")
+# Run inference
+sentences = [
+    'De deur naar de kelderboxen is stuk',
+    'kelderboxen deur',
+    'deur met dranger',
+]
+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           | 0.9821     |
+| cosine_accuracy_threshold | 0.7331     |
+| cosine_f1                 | 0.9821     |
+| cosine_f1_threshold       | 0.7331     |
+| cosine_precision          | 0.9787     |
+| cosine_recall             | 0.9856     |
+| **cosine_ap**             | **0.9973** |
+| cosine_mcc                | 0.9642     |
+
+<!--
+## 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: 68,828 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: 3 tokens</li><li>mean: 7.03 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 6.41 tokens</li><li>max: 18 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>De sluiting van de toegangspoort is stuk</code> | <code>slot defect</code> | <code>1.0</code> |
+  | <code>Woning</code>                                   | <code>trapafgang</code>  | <code>0.0</code> |
+  | <code>De sleutels zijn kwijt</code>                   | <code>Nie</code>         | <code>0.0</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `num_train_epochs`: 10
+- `fp16`: True
+- `multi_dataset_batch_sampler`: round_robin
+
+#### 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`: 64
+- `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`: 10
+- `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
+- `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`: 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`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step  | Training Loss | cosine_ap |
+|:------:|:-----:|:-------------:|:---------:|
+| 0.1998 | 215   | -             | 0.7638    |
+| 0.3996 | 430   | -             | 0.8723    |
+| 0.4647 | 500   | 4.4585        | -         |
+| 0.5994 | 645   | -             | 0.9176    |
+| 0.7993 | 860   | -             | 0.9475    |
+| 0.9294 | 1000  | 3.6015        | -         |
+| 0.9991 | 1075  | -             | 0.9595    |
+| 1.0    | 1076  | -             | 0.9593    |
+| 1.1989 | 1290  | -             | 0.9705    |
+| 1.3941 | 1500  | 3.3729        | -         |
+| 1.3987 | 1505  | -             | 0.9793    |
+| 1.5985 | 1720  | -             | 0.9818    |
+| 1.7983 | 1935  | -             | 0.9854    |
+| 1.8587 | 2000  | 3.2631        | -         |
+| 1.9981 | 2150  | -             | 0.9866    |
+| 2.0    | 2152  | -             | 0.9866    |
+| 2.1980 | 2365  | -             | 0.9890    |
+| 2.3234 | 2500  | 3.1295        | -         |
+| 2.3978 | 2580  | -             | 0.9884    |
+| 2.5976 | 2795  | -             | 0.9916    |
+| 2.7881 | 3000  | 3.0907        | -         |
+| 2.7974 | 3010  | -             | 0.9916    |
+| 2.9972 | 3225  | -             | 0.9922    |
+| 3.0    | 3228  | -             | 0.9922    |
+| 3.1970 | 3440  | -             | 0.9928    |
+| 3.2528 | 3500  | 3.0105        | -         |
+| 3.3968 | 3655  | -             | 0.9932    |
+| 3.5967 | 3870  | -             | 0.9937    |
+| 3.7175 | 4000  | 2.977         | -         |
+| 3.7965 | 4085  | -             | 0.9939    |
+| 3.9963 | 4300  | -             | 0.9944    |
+| 4.0    | 4304  | -             | 0.9945    |
+| 4.1822 | 4500  | 2.9488        | -         |
+| 4.1961 | 4515  | -             | 0.9947    |
+| 4.3959 | 4730  | -             | 0.9950    |
+| 4.5957 | 4945  | -             | 0.9952    |
+| 4.6468 | 5000  | 2.914         | -         |
+| 4.7955 | 5160  | -             | 0.9954    |
+| 4.9954 | 5375  | -             | 0.9956    |
+| 5.0    | 5380  | -             | 0.9956    |
+| 5.1115 | 5500  | 2.8927        | -         |
+| 5.1952 | 5590  | -             | 0.9960    |
+| 5.3950 | 5805  | -             | 0.9959    |
+| 5.5762 | 6000  | 2.8505        | -         |
+| 5.5948 | 6020  | -             | 0.9963    |
+| 5.7946 | 6235  | -             | 0.9961    |
+| 5.9944 | 6450  | -             | 0.9962    |
+| 6.0    | 6456  | -             | 0.9962    |
+| 6.0409 | 6500  | 2.8462        | -         |
+| 6.1942 | 6665  | -             | 0.9963    |
+| 6.3941 | 6880  | -             | 0.9965    |
+| 6.5056 | 7000  | 2.8024        | -         |
+| 6.5939 | 7095  | -             | 0.9967    |
+| 6.7937 | 7310  | -             | 0.9969    |
+| 6.9703 | 7500  | 2.8184        | -         |
+| 6.9935 | 7525  | -             | 0.9968    |
+| 7.0    | 7532  | -             | 0.9967    |
+| 7.1933 | 7740  | -             | 0.9967    |
+| 7.3931 | 7955  | -             | 0.9967    |
+| 7.4349 | 8000  | 2.7761        | -         |
+| 7.5929 | 8170  | -             | 0.9968    |
+| 7.7928 | 8385  | -             | 0.9969    |
+| 7.8996 | 8500  | 2.7736        | -         |
+| 7.9926 | 8600  | -             | 0.9970    |
+| 8.0    | 8608  | -             | 0.9971    |
+| 8.1924 | 8815  | -             | 0.9972    |
+| 8.3643 | 9000  | 2.7627        | -         |
+| 8.3922 | 9030  | -             | 0.9970    |
+| 8.5920 | 9245  | -             | 0.9972    |
+| 8.7918 | 9460  | -             | 0.9972    |
+| 8.8290 | 9500  | 2.7604        | -         |
+| 8.9916 | 9675  | -             | 0.9972    |
+| 9.0    | 9684  | -             | 0.9972    |
+| 9.1914 | 9890  | -             | 0.9971    |
+| 9.2937 | 10000 | 2.7467        | -         |
+| 9.3913 | 10105 | -             | 0.9972    |
+| 9.5911 | 10320 | -             | 0.9973    |
+| 9.7584 | 10500 | 2.7441        | -         |
+| 9.7909 | 10535 | -             | 0.9973    |
+
+
+### Framework Versions
+- Python: 3.11.13
+- Sentence Transformers: 4.1.0
+- Transformers: 4.53.3
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.9.0
+- Datasets: 4.4.1
+- 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",
+}
+```
+
+#### 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,
+  "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": "4.53.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.53.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afff4f9725088bc87e785545f7267fa11e3322962d97ba386cd61b30e25c549
+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": 64,
+  "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:bc5c1151948923156f20bcafd54fd796705d693f8d7b56c83aec49d651f6d602
+size 17082986

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 64,
+  "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