Add new SentenceTransformer model.

.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 +1,405 @@
+---
+base_model: sentence-transformers/paraphrase-xlm-r-multilingual-v1
+datasets: []
+language: []
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:38739
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: '''Turks ve Caicos Adaları''ndaki Afrikalıların nüfusu nedir?'
+  sentences:
+  - "CREATE TABLEethnicGroup (\n    Country TEXT,\n    Name TEXT PRIMARY KEY,\n  \
+    \  Percentage REAL,\n    FOREIGN KEY (Country) REFERENCES country(None)\n);"
+  - "CREATE TABLEPatient (\n    ID INTEGER PRIMARY KEY,\n    SEX TEXT,\n    Birthday\
+    \ DATE,\n    Description DATE,\n    First Date DATE,\n    Admission TEXT,\n  \
+    \  Diagnosis TEXT\n);"
+  - "CREATE TABLEwrites (\n    paperId INTEGER PRIMARY KEY,\n    authorId INTEGER,\n\
+    \    FOREIGN KEY (authorId) REFERENCES author(authorId),\n    FOREIGN KEY (paperId)\
+    \ REFERENCES paper(paperId)\n);"
+- source_sentence: Teksas'ın başkenti nedir
+  sentences:
+  - "CREATE TABLEprofessor (\n    EMP_NUM INT,\n    DEPT_CODE varchar(10),\n    PROF_OFFICE\
+    \ varchar(50),\n    PROF_EXTENSION varchar(4),\n    PROF_HIGH_DEGREE varchar(5),\n\
+    \    FOREIGN KEY (DEPT_CODE) REFERENCES DEPARTMENT(DEPT_CODE),\n    FOREIGN KEY\
+    \ (EMP_NUM) REFERENCES EMPLOYEE(EMP_NUM)\n);"
+  - "CREATE TABLEBusiness_Hours (\n    business_id INTEGER PRIMARY KEY,\n    day_id\
+    \ INTEGER,\n    opening_time TEXT,\n    closing_time TEXT,\n    FOREIGN KEY (day_id)\
+    \ REFERENCES Days(None),\n    FOREIGN KEY (business_id) REFERENCES Business(None)\n\
+    );"
+  - "CREATE TABLEstate (\n    state_name TEXT PRIMARY KEY,\n    population INTEGER,\n\
+    \    area double,\n    country_name varchar(3),\n    capital TEXT,\n    density\
+    \ double\n);"
+- source_sentence: '''Mad Max: Fury Road'' filminde çalışan 10 ekibin işlerinin yanı
+    sıra listeleyin.'
+  sentences:
+  - "CREATE TABLEmovie (\n    movie_id INTEGER PRIMARY KEY,\n    title TEXT,\n   \
+    \ budget INTEGER,\n    homepage TEXT,\n    overview TEXT,\n    popularity REAL,\n\
+    \    release_date DATE,\n    revenue INTEGER,\n    runtime INTEGER,\n    movie_status\
+    \ TEXT,\n    tagline TEXT,\n    vote_average REAL,\n    vote_count INTEGER\n);"
+  - "CREATE TABLEstudent (\n    STU_NUM INT PRIMARY KEY,\n    STU_LNAME varchar(15),\n\
+    \    STU_FNAME varchar(15),\n    STU_INIT varchar(1),\n    STU_DOB datetime,\n\
+    \    STU_HRS INT,\n    STU_CLASS varchar(2),\n    STU_GPA float(8),\n    STU_TRANSFER\
+    \ numeric,\n    DEPT_CODE varchar(18),\n    STU_PHONE varchar(4),\n    PROF_NUM\
+    \ INT,\n    FOREIGN KEY (DEPT_CODE) REFERENCES DEPARTMENT(DEPT_CODE)\n);"
+  - "CREATE TABLEFinancial_transactions (\n    transaction_id INTEGER,\n    account_id\
+    \ INTEGER,\n    invoice_number INTEGER,\n    transaction_type VARCHAR(15),\n \
+    \   transaction_date DATETIME,\n    transaction_amount DECIMAL(19,4),\n    transaction_comment\
+    \ VARCHAR(255),\n    other_transaction_details VARCHAR(255),\n    FOREIGN KEY\
+    \ (account_id) REFERENCES Accounts(account_id),\n    FOREIGN KEY (invoice_number)\
+    \ REFERENCES Invoices(invoice_number)\n);"
+- source_sentence: Tüm müşterilerin ortalama yaşının %80'inden daha büyük yaştaki
+    müşterilerin gelirlerini ve sakin sayısını listeler misiniz?
+  sentences:
+  - "CREATE TABLECustomers (\n    ID INTEGER PRIMARY KEY,\n    SEX TEXT,\n    MARITAL_STATUS\
+    \ TEXT,\n    GEOID INTEGER,\n    EDUCATIONNUM INTEGER,\n    OCCUPATION TEXT,\n\
+    \    age INTEGER,\n    FOREIGN KEY (GEOID) REFERENCES Demog(None)\n);"
+  - "CREATE TABLEauthors (\n    authID INTEGER PRIMARY KEY,\n    lname TEXT,\n   \
+    \ fname TEXT\n);"
+  - "CREATE TABLEcoaches (\n    coachID TEXT PRIMARY KEY,\n    year INTEGER,\n   \
+    \ tmID TEXT,\n    lgID TEXT,\n    stint INTEGER,\n    won INTEGER,\n    lost INTEGER,\n\
+    \    post_wins INTEGER,\n    post_losses INTEGER,\n    FOREIGN KEY (tmID) REFERENCES\
+    \ teams(tmID),\n    FOREIGN KEY (year) REFERENCES teams(year)\n);"
+- source_sentence: Eleanor Hunt'a ait kaç tane kiralama kimliği var?
+  sentences:
+  - "CREATE TABLEsinger (\n    Singer_ID INT PRIMARY KEY,\n    Name TEXT,\n    Country\
+    \ TEXT,\n    Song_Name TEXT,\n    Song_release_year TEXT,\n    Age INT,\n    Is_male\
+    \ bool\n);"
+  - "CREATE TABLEdistrict (\n    District_ID INT PRIMARY KEY,\n    District_name TEXT,\n\
+    \    Headquartered_City TEXT,\n    City_Population REAL,\n    City_Area REAL\n\
+    );"
+  - "CREATE TABLEcustomer (\n    customer_id INTEGER PRIMARY KEY,\n    store_id INTEGER,\n\
+    \    first_name TEXT,\n    last_name TEXT,\n    email TEXT,\n    address_id INTEGER,\n\
+    \    active INTEGER,\n    create_date DATETIME,\n    last_update DATETIME,\n \
+    \   FOREIGN KEY (address_id) REFERENCES address(None),\n    FOREIGN KEY (store_id)\
+    \ REFERENCES store(None)\n);"
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-xlm-r-multilingual-v1
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-xlm-r-multilingual-v1](https://huggingface.co/sentence-transformers/paraphrase-xlm-r-multilingual-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:** [sentence-transformers/paraphrase-xlm-r-multilingual-v1](https://huggingface.co/sentence-transformers/paraphrase-xlm-r-multilingual-v1) <!-- at revision 9df88080e03c09181139a92fdf0423f84a79852d -->
+- **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("nypgd/fine-tuned-sentence-transformer_last")
+# Run inference
+sentences = [
+    "Eleanor Hunt'a ait kaç tane kiralama kimliği var?",
+    'CREATE TABLEcustomer (\n    customer_id INTEGER PRIMARY KEY,\n    store_id INTEGER,\n    first_name TEXT,\n    last_name TEXT,\n    email TEXT,\n    address_id INTEGER,\n    active INTEGER,\n    create_date DATETIME,\n    last_update DATETIME,\n    FOREIGN KEY (address_id) REFERENCES address(None),\n    FOREIGN KEY (store_id) REFERENCES store(None)\n);',
+    'CREATE TABLEdistrict (\n    District_ID INT PRIMARY KEY,\n    District_name TEXT,\n    Headquartered_City TEXT,\n    City_Population REAL,\n    City_Area REAL\n);',
+]
+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.*
+-->
+
+<!--
+## 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: 38,739 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                        | sentence_1                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                             |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 19.22 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 73.6 tokens</li><li>max: 128 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                             | sentence_1                                                                                                                                                                                                                                                                                                                                                                                                     |
+  |:-------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>en büyük alana sahip eyaleti belirtin</code>                                                     | <code>CREATE TABLEstate (<br>    state_name TEXT PRIMARY KEY,<br>    population INTEGER,<br>    area double,<br>    country_name varchar(3),<br>    capital TEXT,<br>    density double<br>);</code>                                                                                                                                                                                                           |
+  | <code>Law & Order'ın hangi bölümleri Primetime Emmy Ödülleri'ne aday gösterildi?</code>                | <code>CREATE TABLEAward (<br>    award_id INTEGER PRIMARY KEY,<br>    organization TEXT,<br>    year INTEGER,<br>    award_category TEXT,<br>    award TEXT,<br>    series TEXT,<br>    episode_id TEXT,<br>    person_id TEXT,<br>    role TEXT,<br>    result TEXT,<br>    FOREIGN KEY (person_id) REFERENCES Person(person_id),<br>    FOREIGN KEY (episode_id) REFERENCES Episode(episode_id)<br>);</code> |
+  | <code>Albümü "Universal Music Group" etiketi altında yer alan tüm şarkıların isimleri nelerdir?</code> | <code>CREATE TABLEtracklists (<br>    AlbumId INTEGER PRIMARY KEY,<br>    Position INTEGER,<br>    SongId INTEGER,<br>    FOREIGN KEY (AlbumId) REFERENCES Albums(AId),<br>    FOREIGN KEY (SongId) REFERENCES Songs(SongId)<br>);</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
+
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 1
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: no
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `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
+- `num_train_epochs`: 1
+- `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
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.2064 | 500  | 0.5621        |
+| 0.4129 | 1000 | 0.295         |
+| 0.6193 | 1500 | 0.2644        |
+| 0.8258 | 2000 | 0.2035        |
+| 1.0322 | 2500 | 0.184         |
+| 1.2386 | 3000 | 0.1237        |
+| 1.4451 | 3500 | 0.1008        |
+| 1.6515 | 4000 | 0.0984        |
+| 1.8580 | 4500 | 0.0841        |
+| 0.2064 | 500  | 0.1214        |
+| 0.4129 | 1000 | 0.1139        |
+| 0.6193 | 1500 | 0.11          |
+| 0.8258 | 2000 | 0.0999        |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.4
+- PyTorch: 2.4.0+cu121
+- Accelerate: 0.32.1
+- Datasets: 2.21.0
+- 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 +1,29 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-xlm-r-multilingual-v1",
+  "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": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.4",
+    "pytorch": "2.4.0+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 sha256:1e76705842847da7eec5bafc1b699fa2639dba8a7000f88322265eed632bffe5
+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": false,
+    "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 sha256:6c2ccb33b55c4d157419a2105d6e033f7514c2baa6306471c56b86ab02787613
+size 17083053

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "full_tokenizer_file": null,
+  "mask_token": "<mask>",
+  "model_max_length": 128,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}