Add new SentenceTransformer model

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

@@ -0,0 +1,551 @@
+---
+base_model: cross-encoder/nli-deberta-v3-large
+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
+- dot_accuracy@1
+- dot_accuracy@3
+- dot_accuracy@5
+- dot_accuracy@10
+- dot_precision@1
+- dot_precision@3
+- dot_precision@5
+- dot_precision@10
+- dot_recall@1
+- dot_recall@3
+- dot_recall@5
+- dot_recall@10
+- dot_ndcg@10
+- dot_mrr@10
+- dot_map@100
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:40338
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: '"Rumpelstilsken, I command the sun to set!"  He seemed to sense
+    a hesitation in his mind, and then the impression of jeweled gears turning.'
+  sentences:
+  - A football game is playing.
+  - He sensed hesitation when commanding Rumpelstiltskin.
+  - I ran and he saw me immediately.
+- source_sentence: A woman wears sunglasses and a black coat as she walks.
+  sentences:
+  - The lady in black walks while wearing her shades.
+  - Two women were walking
+  - The people are running towards the mountains.
+- source_sentence: The Congress relies on GAO to examine virtually every federal program,
+    activity, and policy, as well as institutions that rely on federal funds.
+  sentences:
+  - The men are standing in line at the restaurant.
+  - GAO helps Congress.
+  - Tide permitting, view the shrine from its base to appreciate its full size.
+- source_sentence: The resort was named after Louis James Fraser, an English adventurer
+    and scoundrel, who dealt in mule hides, tin, opium, and gambling.
+  sentences:
+  - A man in front of people.
+  - The resort was named after an English adventurer and scoundrel.
+  - A woman is holding flowers by two men on a bench.
+- source_sentence: Three men riding a bicycle, tow of them are wearing a helmet.
+  sentences:
+  - Accountability measures help establish the financial condition of the government.
+  - A man is pushing a truck.
+  - There are at least two helmets.
+model-index:
+- name: SentenceTransformer based on cross-encoder/nli-deberta-v3-large
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: eval
+      type: eval
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.0003470672814715653
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2842728940453171
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.42875204521790866
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5317318657345431
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.0003470672814715653
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.09475763134843902
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.08575040904358174
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.053173186573454316
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.0003470672814715653
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2842728940453171
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.42875204521790866
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5317318657345431
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2599623819220365
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.17320152646642903
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.1849889511878054
+      name: Cosine Map@100
+    - type: dot_accuracy@1
+      value: 0.003718578015766771
+      name: Dot Accuracy@1
+    - type: dot_accuracy@3
+      value: 0.262531607913134
+      name: Dot Accuracy@3
+    - type: dot_accuracy@5
+      value: 0.40182954038375723
+      name: Dot Accuracy@5
+    - type: dot_accuracy@10
+      value: 0.5089741682780504
+      name: Dot Accuracy@10
+    - type: dot_precision@1
+      value: 0.003718578015766771
+      name: Dot Precision@1
+    - type: dot_precision@3
+      value: 0.08751053597104465
+      name: Dot Precision@3
+    - type: dot_precision@5
+      value: 0.08036590807675144
+      name: Dot Precision@5
+    - type: dot_precision@10
+      value: 0.050897416827805034
+      name: Dot Precision@10
+    - type: dot_recall@1
+      value: 0.003718578015766771
+      name: Dot Recall@1
+    - type: dot_recall@3
+      value: 0.262531607913134
+      name: Dot Recall@3
+    - type: dot_recall@5
+      value: 0.40182954038375723
+      name: Dot Recall@5
+    - type: dot_recall@10
+      value: 0.5089741682780504
+      name: Dot Recall@10
+    - type: dot_ndcg@10
+      value: 0.24760156704826422
+      name: Dot Ndcg@10
+    - type: dot_mrr@10
+      value: 0.16454750021051548
+      name: Dot Mrr@10
+    - type: dot_map@100
+      value: 0.17684391661589097
+      name: Dot Map@100
+---
+
+# SentenceTransformer based on cross-encoder/nli-deberta-v3-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [cross-encoder/nli-deberta-v3-large](https://huggingface.co/cross-encoder/nli-deberta-v3-large). 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:** [cross-encoder/nli-deberta-v3-large](https://huggingface.co/cross-encoder/nli-deberta-v3-large) <!-- at revision 52fab31a566138fbd1f6833a4efc1199f875f05e -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 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: DebertaV2Model 
+  (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})
+)
+```
+
+## 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("richie-ghost/sbert_ft_cross-encoder-nli-deberta-v3-large")
+# Run inference
+sentences = [
+    'Three men riding a bicycle, tow of them are wearing a helmet.',
+    'There are at least two helmets.',
+    'Accountability measures help establish the financial condition of the government.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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
+
+#### Information Retrieval
+* Dataset: `eval`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.0003    |
+| cosine_accuracy@3   | 0.2843    |
+| cosine_accuracy@5   | 0.4288    |
+| cosine_accuracy@10  | 0.5317    |
+| cosine_precision@1  | 0.0003    |
+| cosine_precision@3  | 0.0948    |
+| cosine_precision@5  | 0.0858    |
+| cosine_precision@10 | 0.0532    |
+| cosine_recall@1     | 0.0003    |
+| cosine_recall@3     | 0.2843    |
+| cosine_recall@5     | 0.4288    |
+| cosine_recall@10    | 0.5317    |
+| cosine_ndcg@10      | 0.26      |
+| cosine_mrr@10       | 0.1732    |
+| **cosine_map@100**  | **0.185** |
+| dot_accuracy@1      | 0.0037    |
+| dot_accuracy@3      | 0.2625    |
+| dot_accuracy@5      | 0.4018    |
+| dot_accuracy@10     | 0.509     |
+| dot_precision@1     | 0.0037    |
+| dot_precision@3     | 0.0875    |
+| dot_precision@5     | 0.0804    |
+| dot_precision@10    | 0.0509    |
+| dot_recall@1        | 0.0037    |
+| dot_recall@3        | 0.2625    |
+| dot_recall@5        | 0.4018    |
+| dot_recall@10       | 0.509     |
+| dot_ndcg@10         | 0.2476    |
+| dot_mrr@10          | 0.1645    |
+| dot_map@100         | 0.1768    |
+
+<!--
+## 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: 40,338 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: 5 tokens</li><li>mean: 19.64 tokens</li><li>max: 129 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 11.27 tokens</li><li>max: 36 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                             | sentence_1                                                  |
+  |:---------------------------------------------------------------------------------------|:------------------------------------------------------------|
+  | <code>A group of ladies trying to learn how to belly dance.</code>                     | <code>Several women learn the art of exotic dancing.</code> |
+  | <code>A man and a woman are having a conversation, while the man drinks a beer.</code> | <code>The man is drinking.</code>                           |
+  | <code>A brown dog drinks from a water bottle.</code>                                   | <code>A brown cat drinks from a bowl.</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
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 4
+- `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`: 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
+- `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`: 4
+- `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 | eval_cosine_map@100 |
+|:------:|:-----:|:-------------:|:-------------------:|
+| 0.1983 | 500   | 1.2356        | 0.0873              |
+| 0.3965 | 1000  | 0.4077        | 0.1200              |
+| 0.5948 | 1500  | 0.3205        | 0.1280              |
+| 0.7930 | 2000  | 0.2576        | 0.1416              |
+| 0.9913 | 2500  | 0.2435        | 0.1476              |
+| 1.0    | 2522  | -             | 0.1492              |
+| 1.1895 | 3000  | 0.1821        | 0.1553              |
+| 1.3878 | 3500  | 0.1237        | 0.1589              |
+| 1.5860 | 4000  | 0.1074        | 0.1603              |
+| 1.7843 | 4500  | 0.0905        | 0.1654              |
+| 1.9826 | 5000  | 0.0783        | 0.1685              |
+| 2.0    | 5044  | -             | 0.1683              |
+| 2.1808 | 5500  | 0.0583        | 0.1698              |
+| 2.3791 | 6000  | 0.0432        | 0.1746              |
+| 2.5773 | 6500  | 0.0365        | 0.1749              |
+| 2.7756 | 7000  | 0.0303        | 0.1791              |
+| 2.9738 | 7500  | 0.0276        | 0.1788              |
+| 3.0    | 7566  | -             | 0.1805              |
+| 3.1721 | 8000  | 0.02          | 0.1807              |
+| 3.3703 | 8500  | 0.013         | 0.1823              |
+| 3.5686 | 9000  | 0.0123        | 0.1839              |
+| 3.7669 | 9500  | 0.0099        | 0.1852              |
+| 3.9651 | 10000 | 0.01          | 0.1850              |
+| 4.0    | 10088 | -             | 0.1850              |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.2.1
+- Transformers: 4.44.2
+- PyTorch: 2.5.0+cu121
+- Accelerate: 1.0.1
+- Datasets: 3.0.2
+- 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.*
+-->

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/cross-encoder-nli-deberta-v3-large/save_pretrained",
+  "architectures": [
+    "DebertaV2Model"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "contradiction",
+    "1": "entailment",
+    "2": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "contradiction": 0,
+    "entailment": 1,
+    "neutral": 2
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.5.0+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 sha256:619a968147cbf44d673977b6b3dd7391112a1dff15f1618a086c84e7ac717fb0
+size 1736094384

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 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "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]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}