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 +1,455 @@
+---
+base_model: pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1
+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:5749
+- loss:CosineSimilarityLoss
+widget:
+- source_sentence: আমি "... comoving মহাজাগতিক বিশ্ৰাম ফ্ৰেমৰ তুলনাত ... সিংহ নক্ষত্ৰমণ্ডলৰ
+    ফালে কিছু 371 কিলোমিটাৰ প্ৰতি ছেকেণ্ডত" আগবাঢ়িছো.
+  sentences:
+  - বাস্কেটবল খেলুৱৈগৰাকীয়ে নিজৰ দলৰ হৈ পইণ্ট লাভ কৰিবলৈ ওলাইছে।
+  - আন কোনো বস্তুৰ লগত আপেক্ষিক নহোৱা কোনো ‘ষ্টিল’ নাই।
+  - এজনী ছোৱালীয়ে বতাহ বাদ্যযন্ত্ৰ বজায়।
+- source_sentence: চাৰিটা ল’ৰা-ছোৱালীয়ে ভঁৰালৰ জীৱ-জন্তুবোৰলৈ চাই আছে।
+  sentences:
+  - ডাইনিং টেবুল এখনৰ চাৰিওফালে বৃদ্ধৰ দল এটাই পোজ দিছে।
+  - বিকিনি পিন্ধা চাৰিগৰাকী মহিলাই বিলত ভলীবল খেলি আছে।
+  - ল’ৰা-ছোৱালীয়ে ভেড়া চাই।
+- source_sentence: ডালত বহি থকা দুটা টান ঈগল।
+  sentences:
+  - জাতৰ জেব্ৰা ডানিঅ’ অত্যন্ত কঠোৰ মাছ, ইহঁতক হত্যা কৰাটো প্ৰায় কঠিন।
+  - এটা ডালত দুটা ঈগল বহি আছে।
+  - নূন্যতম মজুৰিৰ আইনসমূহে কম দক্ষ, কম উৎপাদনশীল লোকক আটাইতকৈ বেছি আঘাত দিয়ে।
+- source_sentence: '"মই আচলতে যি বিচাৰিছো সেয়া হৈছে মুছলমান জনসংখ্যাৰ এটা অনুমান..."
+    @ThanosK আৰু @T.E.D., এটা সামগ্ৰিক, সাধাৰণ জনসংখ্যাৰ অনুমান f.e.'
+  sentences:
+  - এগৰাকী মহিলাই সেউজীয়া পিঁয়াজ কাটি আছে।
+  - তলত দিয়া কথাখিনি মোৰ কুকুৰ কাণৰ দৰে কপিৰ পৰা লোৱা হৈছে নিউ পেংগুইন এটলাছ অৱ মেডিভেল
+    হিষ্ট্ৰীৰ।
+  - আমাৰ দৰে সৌৰজগতৰ কোনো তাৰকাৰাজ্যৰ বাহিৰত থকাটো সম্ভৱ হ’ব পাৰে।
+- source_sentence: ইণ্টাৰনেট কেমেৰাৰ জৰিয়তে এগৰাকী ছোৱালীৰ লগত কথা পাতিলে মানুহজনে।
+  sentences:
+  - গছৰ শাৰী এটাৰ সন্মুখত পথাৰত ভেড়া চৰিছে।
+  - এজন মানুহে গীটাৰ বজাই আছে।
+  - ৱেবকেমৰ জৰিয়তে এগৰাকী ছোৱালীৰ সৈতে কথা পাতিছে এজন কিশোৰে।
+model-index:
+- name: SentenceTransformer based on pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1
+  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: 0.8525258323169252
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8506593647943235
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8334889460288037
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.843042040822402
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8351723933495433
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8450734552112781
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8273071926204811
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8277520425148079
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8525258323169252
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8506593647943235
+      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: 0.8138083526567048
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8119367763029309
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8044112753419641
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8073243490029997
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.805728285628756
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8086070843216111
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7754575809083841
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7720173359758135
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8138083526567048
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8119367763029309
+      name: Spearman Max
+---
+
+# SentenceTransformer based on pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1](https://huggingface.co/pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1). 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:** [pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1](https://huggingface.co/pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1) <!-- at revision ec876d6ec1d2030ad233470e574f1d3d3fe56c74 -->
+- **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: 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("pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1-sts")
+# Run inference
+sentences = [
+    'ইণ্টাৰনেট কেমেৰাৰ জৰিয়তে এগৰাকী ছোৱালীৰ লগত কথা পাতিলে মানুহজনে।',
+    'ৱেবকেমৰ জৰিয়তে এগৰাকী ছোৱালীৰ সৈতে কথা পাতিছে এজন কিশোৰে।',
+    'এজন মানুহে গীটাৰ বজাই আছে।',
+]
+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      | 0.8525     |
+| **spearman_cosine** | **0.8507** |
+| pearson_manhattan   | 0.8335     |
+| spearman_manhattan  | 0.843      |
+| pearson_euclidean   | 0.8352     |
+| spearman_euclidean  | 0.8451     |
+| pearson_dot         | 0.8273     |
+| spearman_dot        | 0.8278     |
+| pearson_max         | 0.8525     |
+| spearman_max        | 0.8507     |
+
+#### 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      | 0.8138     |
+| **spearman_cosine** | **0.8119** |
+| pearson_manhattan   | 0.8044     |
+| spearman_manhattan  | 0.8073     |
+| pearson_euclidean   | 0.8057     |
+| spearman_euclidean  | 0.8086     |
+| pearson_dot         | 0.7755     |
+| spearman_dot        | 0.772      |
+| pearson_max         | 0.8138     |
+| spearman_max        | 0.8119     |
+
+<!--
+## 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`: 10
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: 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`: 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`: 10
+- `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`: batch_sampler
+- `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 |
+|:----------:|:-------:|:-------------:|:----------:|:-------------------------------------------------------:|:--------------------------------------------------------:|
+| 1.1111     | 100     | 0.0331        | 0.0259     | 0.8482                                                  | -                                                        |
+| **2.2222** | **200** | **0.0176**    | **0.0253** | **0.8515**                                              | **-**                                                    |
+| 3.3333     | 300     | 0.011         | 0.0253     | 0.8513                                                  | -                                                        |
+| 4.4444     | 400     | 0.0066        | 0.0259     | 0.8492                                                  | -                                                        |
+| 5.5556     | 500     | 0.0048        | 0.0255     | 0.8511                                                  | -                                                        |
+| 6.6667     | 600     | 0.0037        | 0.0256     | 0.8508                                                  | -                                                        |
+| 7.7778     | 700     | 0.0033        | 0.0254     | 0.8515                                                  | -                                                        |
+| 8.8889     | 800     | 0.0029        | 0.0255     | 0.8512                                                  | -                                                        |
+| 10.0       | 900     | 0.0027        | 0.0257     | 0.8507                                                  | 0.8119                                                   |
+
+* 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",
+}
+```
+
+<!--
+## 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": "output/training_stsbenchmark_pritamdeka-muril-base-cased-assamese-indicxnli-random-negatives-v1-2024-07-17_18-57-25/final",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 197285
+}

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:cd6cb1d692d0c34cc3bf3907a77988d854096788095631d2d852af13ae4fcf12
+size 950247272

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 +1,65 @@
+{
+  "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
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "lowercase": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "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": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}