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": 1024,
+    "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

@@ -1,3 +1,506 @@
----
-license: apache-2.0
----
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:76932
+- loss:MultipleNegativesRankingLoss
+base_model: intfloat/multilingual-e5-large
+widget:
+- source_sentence: 'query: ATM Adaptation Layer 2의 약어는 무엇인가요?'
+  sentences:
+  - 'passage: 2 Transmit 2 Receive (기술)'
+  - 'passage: Alternating Current (개념)'
+  - 'passage: AAL2 (기술)'
+- source_sentence: 'query: AC의 접근 클래스 C0부터 C15까지의 기능은 무엇인가요?'
+  sentences:
+  - 'passage: Access Class (C0 to C15) (개념)'
+  - 'passage: 3 Dimension-Through Silicon Via (기술)'
+  - 'passage: ACAP (Conceptual)'
+- source_sentence: 'query: What is the abbreviation for Alarm Agent Handling Block?'
+  sentences:
+  - 'passage: ATM Connection establishment/release Control Block (기술)'
+  - 'passage: AAGHB (Technical)'
+  - 'passage: Account Card Calling (활용)'
+- source_sentence: 'query: ABPL의 ATM 기본 속도 물리 계층 장치는 어떻게 구성되어 있나요?'
+  sentences:
+  - 'passage: ATM Base Rate Physical Layer Unit (기술)'
+  - 'passage: 3A (개념)'
+  - 'passage: 5GTF (Conceptual)'
+- source_sentence: 'query: How does the triple encryption process of 3-DES enhance
+    security?'
+  sentences:
+  - 'passage: 5th Generation Technical Forum (Conceptual)'
+  - 'passage: Triple Data Encryption Standard (Technical)'
+  - 'passage: ABCDEF (활용)'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on intfloat/multilingual-e5-large
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: e5 eval real
+      type: e5-eval-real
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.8686666666666667
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.969
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9832
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9922
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.8686666666666667
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.323
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19664000000000004
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09922000000000002
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8686666666666667
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.969
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9832
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9922
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9376619313817377
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9193550000000039
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9197550584627825
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on intfloat/multilingual-e5-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) on the train dataset. It maps sentences & paragraphs to a 1024-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:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) <!-- at revision 0dc5580a448e4284468b8909bae50fa925907bc5 -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - train
+<!-- - **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': 256, 'do_lower_case': False, 'architecture': 'XLMRobertaModel'})
+  (1): Pooling({'word_embedding_dimension': 1024, '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})
+  (2): Normalize()
+)
+```
+
+## 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 = [
+    'query: How does the triple encryption process of 3-DES enhance security?',
+    'passage: Triple Data Encryption Standard (Technical)',
+    'passage: ABCDEF (활용)',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[1.0000, 0.8389, 0.1546],
+#         [0.8389, 1.0000, 0.0850],
+#         [0.1546, 0.0850, 1.0000]])
+```
+
+<!--
+### 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
+
+#### Information Retrieval
+
+* Dataset: `e5-eval-real`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.8687     |
+| cosine_accuracy@3   | 0.969      |
+| cosine_accuracy@5   | 0.9832     |
+| cosine_accuracy@10  | 0.9922     |
+| cosine_precision@1  | 0.8687     |
+| cosine_precision@3  | 0.323      |
+| cosine_precision@5  | 0.1966     |
+| cosine_precision@10 | 0.0992     |
+| cosine_recall@1     | 0.8687     |
+| cosine_recall@3     | 0.969      |
+| cosine_recall@5     | 0.9832     |
+| cosine_recall@10    | 0.9922     |
+| **cosine_ndcg@10**  | **0.9377** |
+| cosine_mrr@10       | 0.9194     |
+| cosine_map@100      | 0.9198     |
+
+<!--
+## 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
+
+#### train
+
+* Dataset: train
+* Size: 76,932 training samples
+* Columns: <code>0</code> and <code>1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | 0                                                                                  | 1                                                                                 |
+  |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 11 tokens</li><li>mean: 19.44 tokens</li><li>max: 48 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 12.28 tokens</li><li>max: 27 tokens</li></ul> |
+* Samples:
+  | 0                                                                   | 1                                                                 |
+  |:--------------------------------------------------------------------|:------------------------------------------------------------------|
+  | <code>query: 3D-TSV 기술의 구조는 어떻게 되어 있나요?</code>                      | <code>passage: 3 Dimension-Through Silicon Via (기술)</code>        |
+  | <code>query: What is the structure of the 3D-TSV technology?</code> | <code>passage: 3 Dimension-Through Silicon Via (Technical)</code> |
+  | <code>query: 3 Dimension-Through Silicon Via의 줄임말이 뭐죠?</code>       | <code>passage: 3D-TSV (기술)</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",
+      "gather_across_devices": false
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `learning_rate`: 1e-05
+- `weight_decay`: 0.01
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: 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
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 1e-05
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `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`: True
+- `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}
+- `parallelism_config`: None
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `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`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | e5-eval-real_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------------------:|
+| 0.0008 | 1    | 3.1575        | -                           |
+| 0.0831 | 100  | 1.6593        | -                           |
+| 0.1663 | 200  | 0.1298        | 0.8389                      |
+| 0.2494 | 300  | 0.0848        | -                           |
+| 0.3325 | 400  | 0.0716        | 0.8808                      |
+| 0.4156 | 500  | 0.0504        | -                           |
+| 0.4988 | 600  | 0.0421        | 0.9033                      |
+| 0.5819 | 700  | 0.042         | -                           |
+| 0.6650 | 800  | 0.0398        | 0.9095                      |
+| 0.7481 | 900  | 0.0384        | -                           |
+| 0.8313 | 1000 | 0.0383        | 0.9111                      |
+| 0.9144 | 1100 | 0.0321        | -                           |
+| 0.9975 | 1200 | 0.0317        | 0.9186                      |
+| 1.0806 | 1300 | 0.0299        | -                           |
+| 1.1638 | 1400 | 0.0302        | 0.9161                      |
+| 1.2469 | 1500 | 0.025         | -                           |
+| 1.3300 | 1600 | 0.0199        | 0.9261                      |
+| 1.4131 | 1700 | 0.0179        | -                           |
+| 1.4963 | 1800 | 0.0117        | 0.9305                      |
+| 1.5794 | 1900 | 0.013         | -                           |
+| 1.6625 | 2000 | 0.012         | 0.9308                      |
+| 1.7456 | 2100 | 0.0137        | -                           |
+| 1.8288 | 2200 | 0.0141        | 0.9309                      |
+| 1.9119 | 2300 | 0.0127        | -                           |
+| 1.9950 | 2400 | 0.0115        | 0.9332                      |
+| 2.0781 | 2500 | 0.0114        | -                           |
+| 2.1613 | 2600 | 0.011         | 0.9351                      |
+| 2.2444 | 2700 | 0.0107        | -                           |
+| 2.3275 | 2800 | 0.0087        | 0.9357                      |
+| 2.4106 | 2900 | 0.0084        | -                           |
+| 2.4938 | 3000 | 0.0059        | 0.9366                      |
+| 2.5769 | 3100 | 0.0062        | -                           |
+| 2.6600 | 3200 | 0.0071        | 0.9377                      |
+| 2.7431 | 3300 | 0.0072        | -                           |
+| 2.8263 | 3400 | 0.0079        | 0.9376                      |
+| 2.9094 | 3500 | 0.0071        | -                           |
+| 2.9925 | 3600 | 0.0068        | 0.9376                      |
+| -1     | -1   | -             | 0.9377                      |
+
+
+### Framework Versions
+- Python: 3.12.11
+- Sentence Transformers: 5.1.0
+- Transformers: 4.56.1
+- PyTorch: 2.8.0+cu126
+- Accelerate: 1.10.1
+- Datasets: 3.6.0
+- Tokenizers: 0.22.0
+
+## 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 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.1.0",
+    "transformers": "4.56.1",
+    "pytorch": "2.8.0+cu126"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d7068475f633c0337dc3d2676dca52e219d0cc57e7a6e68ea57fdd0b6f67c8
+size 2239607176

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 256,
+    "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:a514807cffabd8abaf028cfaffe7ff0c4f60b97ea2db80c41f14172ae6b018ca
+size 17082987

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}