Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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

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 +1,447 @@
+---
+library_name: sentence-transformers
+metrics:
+- negative_mse
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:25095
+- loss:MSELoss
+widget:
+- source_sentence: mariknak pay ketdi a naabrasaak iti kulonganda
+  sentences:
+  - Nakuha nako ang usa ka kuptanan sa istorya ug nagsugod kini sa pagbati ug porma
+    nga akong gusto
+  - 'Ang kasarangang pag-ulan sa London, nga adunay kataas nga 10°C ug ang ubos nga
+    6°C. #LondonWeather #RainyDay'
+  - Controversial religious text causes uproar among community members
+- source_sentence: "JUAN COLE: Ang Pagduso sa Islamic State sa Baghdad 'Usa ka\
+    \ Pagsulay Aron Mabawi ang Gikuha sa Bush Administration' \n"
+  sentences:
+  - Ang Touchdown nga Selebrasyon ni Antonio Brown Sexy Gihapon Alang sa NFL Bisan
+    ang duha ka pagduso makapasilo kanimo.
+  - Natuklasan ng mga siyentipiko ang mga bagong species ng nilalang sa malalim na
+    dagat
+  - i feel so glad doing this
+- source_sentence: New Curriculum Standards to Be Implemented in All Schools Next
+    Year
+  sentences:
+  - "Climate Change This Week: Mega Methane, Tidal Power, and More \n"
+  - '@lilomatic Only in Zimbabwe where u find Opposition party for another Opposition
+    party.'
+  - "Ang mamumuno nga si Mike namulong sa Ferguson: 'Ang Hustisya Dili Kanunay\
+    \ Gisilbi' \n"
+- source_sentence: i am so blessed and feel blessed to be able to share my creations
+    with you
+  sentences:
+  - "Ania ang Buhaton Sa World Cup Host Cities Gawas sa Pagtan-aw sa Soccer \n"
+  - "Hillary Clinton's 'Super Volunteers' Are Back And Ready For 2016 \n"
+  - Awan pay ti koriente para kadagiti paset ti Joburg kalpasan ti uram ti kable iti
+    uneg ti daga https://t.co/szuZa380Lr
+- source_sentence: "3 Napateg nga Addang (iti Aniaman nga Edad) tapno Agsagana iti\
+    \ Matay \n"
+  sentences:
+  - EPIC! RAND PAUL Laughs at CNN’s Climate Hysteria…Schools Jake Tapper on Climate
+    Truth [Video]
+  - im feeling horrible
+  - 'Image: WC Provincial Disaster Management Centre https://t.co/EcNgpBhjcV'
+model-index:
+- name: SentenceTransformer
+  results:
+  - task:
+      type: knowledge-distillation
+      name: Knowledge Distillation
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: negative_mse
+      value: -0.2521140966564417
+      name: Negative Mse
+---
+
+# SentenceTransformer
+
+This is a [sentence-transformers](https://www.SBERT.net) model trained. 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:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 128 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': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    '3 Napateg nga Addang (iti Aniaman nga Edad) tapno Agsagana iti Matay \n',
+    'EPIC! RAND PAUL Laughs at CNN’s Climate Hysteria…Schools Jake Tapper on Climate Truth [Video]',
+    'Image: WC Provincial Disaster Management Centre https://t.co/EcNgpBhjcV',
+]
+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
+
+#### Knowledge Distillation
+
+* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.MSEEvaluator)
+
+| Metric           | Value       |
+|:-----------------|:------------|
+| **negative_mse** | **-0.2521** |
+
+<!--
+## 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: 25,095 training samples
+* Columns: <code>sentence_0</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                        | label                                |
+  |:--------|:----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                            | list                                 |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 23.49 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | sentence_0                                                                                | label                                                                                                                             |
+  |:------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------|
+  | <code>A suicide bomber targeting a crowded market resulting in numerous fatalities</code> | <code>[-0.05337272211909294, -0.296869158744812, -0.005234384443610907, -0.017071111127734184, 0.01954558491706848, ...]</code>   |
+  | <code>Jeb Bush To Meet With Charleston Pastors <br></code>                                | <code>[-0.025684779509902, 0.2293000966310501, -0.005389949772506952, 0.09448838979005814, 0.017471183091402054, ...]</code>      |
+  | <code>New scientific research suggests link between air pollution and lung disease</code> | <code>[-0.12967786192893982, 0.19541345536708832, -0.0044404976069927216, -0.06291326135396957, -0.03776596114039421, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#mseloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `num_train_epochs`: 20
+- `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`: 20
+- `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`: False
+- `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
+- `eval_use_gather_object`: False
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch   | Step | Training Loss | negative_mse |
+|:-------:|:----:|:-------------:|:------------:|
+| 0.5089  | 200  | -             | -0.3720      |
+| 1.0     | 393  | -             | -0.3428      |
+| 1.0178  | 400  | -             | -0.3437      |
+| 1.2723  | 500  | 0.0024        | -            |
+| 1.5267  | 600  | -             | -0.3262      |
+| 2.0     | 786  | -             | -0.3153      |
+| 2.0356  | 800  | -             | -0.3156      |
+| 2.5445  | 1000 | 0.0018        | -0.3070      |
+| 3.0     | 1179 | -             | -0.3004      |
+| 3.0534  | 1200 | -             | -0.3005      |
+| 3.5623  | 1400 | -             | -0.2959      |
+| 3.8168  | 1500 | 0.0015        | -            |
+| 4.0     | 1572 | -             | -0.2907      |
+| 4.0712  | 1600 | -             | -0.2924      |
+| 4.5802  | 1800 | -             | -0.2863      |
+| 5.0     | 1965 | -             | -0.2831      |
+| 5.0891  | 2000 | 0.0013        | -0.2841      |
+| 5.5980  | 2200 | -             | -0.2792      |
+| 6.0     | 2358 | -             | -0.2765      |
+| 6.1069  | 2400 | -             | -0.2774      |
+| 6.3613  | 2500 | 0.0012        | -            |
+| 6.6158  | 2600 | -             | -0.2734      |
+| 7.0     | 2751 | -             | -0.2716      |
+| 7.1247  | 2800 | -             | -0.2722      |
+| 7.6336  | 3000 | 0.0011        | -0.2700      |
+| 8.0     | 3144 | -             | -0.2684      |
+| 8.1425  | 3200 | -             | -0.2683      |
+| 8.6514  | 3400 | -             | -0.2665      |
+| 8.9059  | 3500 | 0.001         | -            |
+| 9.0     | 3537 | -             | -0.2645      |
+| 9.1603  | 3600 | -             | -0.2649      |
+| 9.6692  | 3800 | -             | -0.2639      |
+| 10.0    | 3930 | -             | -0.2625      |
+| 10.1781 | 4000 | 0.0009        | -0.2619      |
+| 10.6870 | 4200 | -             | -0.2615      |
+| 11.0    | 4323 | -             | -0.2594      |
+| 11.1959 | 4400 | -             | -0.2598      |
+| 11.4504 | 4500 | 0.0009        | -            |
+| 11.7048 | 4600 | -             | -0.2587      |
+| 12.0    | 4716 | -             | -0.2582      |
+| 12.2137 | 4800 | -             | -0.2586      |
+| 12.7226 | 5000 | 0.0008        | -0.2573      |
+| 13.0    | 5109 | -             | -0.2568      |
+| 13.2316 | 5200 | -             | -0.2567      |
+| 13.7405 | 5400 | -             | -0.2564      |
+| 13.9949 | 5500 | 0.0008        | -            |
+| 14.0    | 5502 | -             | -0.2558      |
+| 14.2494 | 5600 | -             | -0.2560      |
+| 14.7583 | 5800 | -             | -0.2551      |
+| 15.0    | 5895 | -             | -0.2548      |
+| 15.2672 | 6000 | 0.0008        | -0.2552      |
+| 15.7761 | 6200 | -             | -0.2540      |
+| 16.0    | 6288 | -             | -0.2534      |
+| 16.2850 | 6400 | -             | -0.2538      |
+| 16.5394 | 6500 | 0.0008        | -            |
+| 16.7939 | 6600 | -             | -0.2529      |
+| 17.0    | 6681 | -             | -0.2532      |
+| 17.3028 | 6800 | -             | -0.2530      |
+| 17.8117 | 7000 | 0.0008        | -0.2528      |
+| 18.0    | 7074 | -             | -0.2525      |
+| 18.3206 | 7200 | -             | -0.2527      |
+| 18.8295 | 7400 | -             | -0.2521      |
+
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.1.1
+- Transformers: 4.44.2
+- PyTorch: 2.4.0
+- Accelerate: 0.34.2
+- Datasets: 3.0.0
+- 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",
+}
+```
+
+#### MSELoss
+```bibtex
+@inproceedings{reimers-2020-multilingual-sentence-bert,
+    title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2020",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/2004.09813",
+}
+```
+
+<!--
+## 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.*
+-->

Score_Metric.csv

@@ -0,0 +1,7 @@
+task,Language,acc,bacc,mcc,f1,baseline_acc,baseline_bacc,baseline_mcc,baseline_f1
+theme,Cebuano,0.52,0.69,0.5,0.52,0.48,0.37,0.4,0.4
+theme,Filipino (Tagalog),0.52,0.69,0.5,0.52,0.48,0.37,0.4,0.4
+theme,Ilocano,0.52,0.69,0.5,0.52,0.48,0.37,0.4,0.4
+sentiment,Cebuano,0.61,0.65,0.43,0.61,0.55,0.46,0.28,0.44
+sentiment,Filipino (Tagalog),0.61,0.65,0.43,0.61,0.55,0.46,0.28,0.44
+sentiment,Ilocano,0.61,0.65,0.43,0.61,0.55,0.46,0.28,0.44

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/kaggle/input/mpnet-extended-fil-ceb-iloc/output/mpnet-multilingual-eng-or-ti-ha-am",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.4.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c05067fed3d84b77872a0119855be1c38c7b4faad9940bed9513043781944c6
+size 1112197096

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
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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 +1,61 @@
+{
+  "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>",
+  "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,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}