Add new SentenceTransformer model.

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 +1,485 @@
+---
+base_model: distilbert/distilbert-base-multilingual-cased
+datasets: []
+language: []
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:654495
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: সম্পূৰ্ণৰূপে ভিন্ন ধৰণৰ পেৰাচুট আৰু এটা উড়ন্ত পক্ষীৰ মাজত, আহ্,
+    শব্দৰ তিনিগুণ বেগত, ঘণ্টাৰ ২২, ০০০ মাইলত।
+  sentences:
+  - ঘণ্টাৰ ২০, ০০০ কিলোমিটাৰতকৈ অধিক গতিত উড়ে।
+  - মোৰ ঘৰত দুটা কম্পিউটাৰ আছে।
+  - সকলো ক্ৰীড়াৰ নাম ক্ৰীড়াত ব্যৱহাৰ কৰা এটা সঁজুলিৰ নামেৰে নামকৰণ কৰা হয়।
+- source_sentence: আৰু তাৰ পিছত মই তেওঁক যাবলৈ শুনিছিলোঁ, সেয়েহে মই এতিয়াও মোৰ কাম
+    শেষ কৰি আছো।
+  sentences:
+  - মই আজি যিটো কৰিব লাগিব সেয়া কৰি আছো।
+  - '"Bato (বা" "vato" ") এটা স্পেনিছ শব্দ যাৰ অৰ্থ হৈছে" "পুৰুষ" "বা" "বন্ধু" "।"'
+  - পিতৃ-মাতৃয়ে ঘৰত থাকিল।
+- source_sentence: মই কেৱল বুজাবলৈ চেষ্টা কৰিছিলোঁ।
+  sentences:
+  - মই বুজিবলৈ চেষ্টা কৰিছিলোঁ।
+  - মই আন কেইবাটাও প্ৰস্তাৱ দিবলৈ আহিছিলোঁ।
+  - প্ৰেমিক নামৰ এজন খেতিয়কে নিজৰ হত্যাৰ আঁচনি তৈয়াৰ কৰোতে ঘাসপূৰ্ণ স্থানত লুকুৱাই
+    থৈ যায়।
+- source_sentence: আৰু, উম, যদি এইটো বাঢ়ি আহিব আৰু কেৱল বাঢ়ি আহিব তেতিয়াহ 'লে'
+    whish 'হ' ব, আৰু যেনেকৈ ই আপোনাৰ মূৰটো বন্ধ কৰি দিব।
+  sentences:
+  - প্ৰাৰম্ভিক শিক্ষা লাভ কৰা আৰু বয়সস্থ ল 'ৰা-ছোৱালীয়ে প্ৰায়ে ভৱিষ্যতৰ বিষয়ে
+    সপোন দেখে।
+  - তেওঁলোকে মোৰ ওচৰলৈ কিয় আহিছে বুলি প্ৰশ্ন কৰিলে।
+  - যদি কোনো ধৰণৰ পৰিৱৰ্তন হয়, তেনেহ 'লে তাৰ লগত এক শব্দ বাঢ়িব পাৰে।
+- source_sentence: মই ভালদৰে জানিব নোৱাৰোঁ আপোনালোকৰ সৈতে কথা বতৰা আৰু এক ভাল সন্ধ্যা
+    আছিল
+  sentences:
+  - মই নিশ্চিত নহয় কিন্তু মই অলপ ভাল, আজি ৰাতি আপোনালোকৰ সৈতে কথা পাতিবলৈ পাই ভাল
+    লাগিল।
+  - Shannon এ বাৰ্তা উপেক্ষা কৰিছে।
+  - মানুহজনে ষ্টক এক্সচেঞ্জত লেনদেনৰ বিষয়ে জানিবলৈ চেষ্টা কৰিছিল।
+model-index:
+- name: SentenceTransformer based on distilbert/distilbert-base-multilingual-cased
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: pritamdeka/stsb assamese translated dev
+      type: pritamdeka/stsb-assamese-translated-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.7169579983340281
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.7220987460972806
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.7380110422340219
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.7452082040848071
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.7386577662108481
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.7458961406429292
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6480820840127198
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6478256799308721
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.7386577662108481
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.7458961406429292
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: pritamdeka/stsb assamese translated test
+      type: pritamdeka/stsb-assamese-translated-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.656822131496386
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6621886312595516
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.6675496858061083
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6722470705036974
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.6681862838868354
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6727345795749732
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5691955650489428
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.570867962692759
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.6681862838868354
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6727345795749732
+      name: Spearman Max
+---
+
+# SentenceTransformer based on distilbert/distilbert-base-multilingual-cased
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased). 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:** [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) <!-- at revision 45c032ab32cc946ad88a166f7cb282f58c753c2e -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 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': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel 
+  (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("pritamdeka/distilbert-base-multilingual-cased-indicxnli-random-negatives-v1")
+# Run inference
+sentences = [
+    'মই ভালদৰে জানিব নোৱাৰোঁ আপোনালোকৰ সৈতে কথা বতৰা আৰু এক ভাল সন্ধ্যা আছিল',
+    'মই নিশ্চিত নহয় কিন্তু মই অলপ ভাল, আজি ৰাতি আপোনালোকৰ সৈতে কথা পাতিবলৈ পাই ভাল লাগিল।',
+    'Shannon এ বাৰ্তা উপেক্ষা কৰিছে।',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# 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
+
+#### Semantic Similarity
+* Dataset: `pritamdeka/stsb-assamese-translated-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.717      |
+| **spearman_cosine** | **0.7221** |
+| pearson_manhattan   | 0.738      |
+| spearman_manhattan  | 0.7452     |
+| pearson_euclidean   | 0.7387     |
+| spearman_euclidean  | 0.7459     |
+| pearson_dot         | 0.6481     |
+| spearman_dot        | 0.6478     |
+| pearson_max         | 0.7387     |
+| spearman_max        | 0.7459     |
+
+#### Semantic Similarity
+* Dataset: `pritamdeka/stsb-assamese-translated-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6568     |
+| **spearman_cosine** | **0.6622** |
+| pearson_manhattan   | 0.6675     |
+| spearman_manhattan  | 0.6722     |
+| pearson_euclidean   | 0.6682     |
+| spearman_euclidean  | 0.6727     |
+| pearson_dot         | 0.5692     |
+| spearman_dot        | 0.5709     |
+| pearson_max         | 0.6682     |
+| spearman_max        | 0.6727     |
+
+<!--
+## 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`: 64
+- `per_device_eval_batch_size`: 64
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `batch_sampler`: no_duplicates
+
+#### 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
+- `learning_rate`: 5e-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`: 0.1
+- `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`: 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`: 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`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step      | Training Loss | loss       | pritamdeka/stsb-assamese-translated-dev_spearman_cosine | pritamdeka/stsb-assamese-translated-test_spearman_cosine |
+|:----------:|:---------:|:-------------:|:----------:|:-------------------------------------------------------:|:--------------------------------------------------------:|
+| 0          | 0         | -             | -          | 0.5489                                                  | -                                                        |
+| 0.0489     | 500       | 1.9387        | 1.7308     | 0.6808                                                  | -                                                        |
+| 0.0978     | 1000      | 1.0503        | 1.7373     | 0.6689                                                  | -                                                        |
+| 0.1467     | 1500      | 0.92          | 1.5838     | 0.6761                                                  | -                                                        |
+| 0.1956     | 2000      | 0.8754        | 1.4807     | 0.6518                                                  | -                                                        |
+| 0.2445     | 2500      | 0.7988        | 1.3797     | 0.6853                                                  | -                                                        |
+| 0.2933     | 3000      | 0.7606        | 1.3713     | 0.7108                                                  | -                                                        |
+| 0.3422     | 3500      | 0.7228        | 1.2510     | 0.6677                                                  | -                                                        |
+| 0.3911     | 4000      | 0.688         | 1.2374     | 0.6734                                                  | -                                                        |
+| 0.4400     | 4500      | 0.6992        | 1.2173     | 0.6891                                                  | -                                                        |
+| 0.4889     | 5000      | 0.6108        | 1.1638     | 0.7017                                                  | -                                                        |
+| 0.5378     | 5500      | 0.612         | 1.0815     | 0.7102                                                  | -                                                        |
+| 0.5867     | 6000      | 0.6259        | 1.0664     | 0.7202                                                  | -                                                        |
+| 0.6356     | 6500      | 0.5863        | 1.0464     | 0.7047                                                  | -                                                        |
+| 0.6845     | 7000      | 0.5941        | 1.0111     | 0.7101                                                  | -                                                        |
+| 0.7334     | 7500      | 0.5436        | 1.0023     | 0.7171                                                  | -                                                        |
+| 0.7822     | 8000      | 0.555         | 0.9633     | 0.7202                                                  | -                                                        |
+| 0.8311     | 8500      | 0.5466        | 0.9651     | 0.7279                                                  | -                                                        |
+| 0.8800     | 9000      | 0.5326        | 0.9611     | 0.7262                                                  | -                                                        |
+| 0.9289     | 9500      | 0.5055        | 0.9313     | 0.7276                                                  | -                                                        |
+| **0.9778** | **10000** | **0.4828**    | **0.9172** | **0.7221**                                              | **-**                                                    |
+| 1.0        | 10227     | -             | -          | -                                                       | 0.6622                                                   |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.4
+- PyTorch: 2.3.1+cu121
+- Accelerate: 0.32.1
+- Datasets: 2.20.0
+- 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",
+}
+```
+
+#### 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 @@
+{
+  "_name_or_path": "output/training_nli_v2_distilbert-distilbert-base-multilingual-cased-2024-07-17_18-23-02/final",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "vocab_size": 119547
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.4",
+    "pytorch": "2.3.1+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 sha256:889aea5cebb8fcda150d279cb4147adb1db46ca2e57679bb212046146e3c3cc7
+size 538947416

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": 512,
+  "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 +1,62 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "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": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}