Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,592 @@
+---
+base_model: colorfulscoop/sbert-base-ja
+datasets: []
+language: []
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- manhattan_accuracy
+- manhattan_accuracy_threshold
+- manhattan_f1
+- manhattan_f1_threshold
+- manhattan_precision
+- manhattan_recall
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_accuracy_threshold
+- euclidean_f1
+- euclidean_f1_threshold
+- euclidean_precision
+- euclidean_recall
+- euclidean_ap
+- max_accuracy
+- max_accuracy_threshold
+- max_f1
+- max_f1_threshold
+- max_precision
+- max_recall
+- max_ap
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:124
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: なにも要らない
+  sentences:
+  - 欲しくない
+  - 暖炉を調べよう
+  - キャンドルがいいな
+- source_sentence: 試すため
+  sentences:
+  - 誰にもらったやつ？
+  - スカーフはナイトスタンドにある？
+  - ためすため
+- source_sentence: ビーフシチュー作った？
+  sentences:
+  - 昨日作ったのはビーフシチュー？
+  - キャンドル要らない
+  - 昨日夕飯にビーフシチュー食べた？
+- source_sentence: あれってキミのスカーフ？
+  sentences:
+  - あの木の上にあるやつはなに？
+  - あれってレオのスカーフ？
+  - どっちをさがせばいい？
+- source_sentence: どっちも欲しくない
+  sentences:
+  - 気にスカーフがひっかかってる
+  - 花壇を調べよう
+  - タイマツ要らない
+model-index:
+- name: SentenceTransformer based on colorfulscoop/sbert-base-ja
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: custom arc semantics data
+      type: custom-arc-semantics-data
+    metrics:
+    - type: cosine_accuracy
+      value: 0.967741935483871
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.2947738766670227
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9836065573770492
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.2947738766670227
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 1.0
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.967741935483871
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9999999999999998
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.967741935483871
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 144.98019409179688
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.9836065573770492
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 144.98019409179688
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 1.0
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.967741935483871
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.9999999999999998
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.967741935483871
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 585.5504150390625
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.9836065573770492
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 585.5504150390625
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 1.0
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.967741935483871
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.9999999999999998
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.967741935483871
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 26.343276977539062
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.9836065573770492
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 26.343276977539062
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 1.0
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.967741935483871
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.9999999999999998
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.967741935483871
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 585.5504150390625
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.9836065573770492
+      name: Max F1
+    - type: max_f1_threshold
+      value: 585.5504150390625
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 1.0
+      name: Max Precision
+    - type: max_recall
+      value: 0.967741935483871
+      name: Max Recall
+    - type: max_ap
+      value: 0.9999999999999998
+      name: Max Ap
+---
+
+# SentenceTransformer based on colorfulscoop/sbert-base-ja
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja). 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:** [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) <!-- at revision ecb8a98cd5176719ff7ab0d770a27420118732cf -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("LeoChiuu/sbert-base-ja-arc")
+# Run inference
+sentences = [
+    'どっちも欲しくない',
+    'タイマツ要らない',
+    '花壇を調べよう',
+]
+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
+
+#### Binary Classification
+* Dataset: `custom-arc-semantics-data`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value    |
+|:-----------------------------|:---------|
+| cosine_accuracy              | 0.9677   |
+| cosine_accuracy_threshold    | 0.2948   |
+| cosine_f1                    | 0.9836   |
+| cosine_f1_threshold          | 0.2948   |
+| cosine_precision             | 1.0      |
+| cosine_recall                | 0.9677   |
+| cosine_ap                    | 1.0      |
+| dot_accuracy                 | 0.9677   |
+| dot_accuracy_threshold       | 144.9802 |
+| dot_f1                       | 0.9836   |
+| dot_f1_threshold             | 144.9802 |
+| dot_precision                | 1.0      |
+| dot_recall                   | 0.9677   |
+| dot_ap                       | 1.0      |
+| manhattan_accuracy           | 0.9677   |
+| manhattan_accuracy_threshold | 585.5504 |
+| manhattan_f1                 | 0.9836   |
+| manhattan_f1_threshold       | 585.5504 |
+| manhattan_precision          | 1.0      |
+| manhattan_recall             | 0.9677   |
+| manhattan_ap                 | 1.0      |
+| euclidean_accuracy           | 0.9677   |
+| euclidean_accuracy_threshold | 26.3433  |
+| euclidean_f1                 | 0.9836   |
+| euclidean_f1_threshold       | 26.3433  |
+| euclidean_precision          | 1.0      |
+| euclidean_recall             | 0.9677   |
+| euclidean_ap                 | 1.0      |
+| max_accuracy                 | 0.9677   |
+| max_accuracy_threshold       | 585.5504 |
+| max_f1                       | 0.9836   |
+| max_f1_threshold             | 585.5504 |
+| max_precision                | 1.0      |
+| max_recall                   | 0.9677   |
+| **max_ap**                   | **1.0**  |
+
+<!--
+## 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: 124 training samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text1                                                                            | text2                                                                            | label                        |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------|
+  | type    | string                                                                           | string                                                                           | int                          |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 8.59 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 8.58 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>1: 100.00%</li></ul> |
+* Samples:
+  | text1                   | text2                  | label          |
+  |:------------------------|:-----------------------|:---------------|
+  | <code>昨晩何を食べたの？</code>  | <code>昨夜何を食べたの？</code> | <code>1</code> |
+  | <code>スリッパをはいたの？</code> | <code>スリッパはいてた？</code> | <code>1</code> |
+  | <code>家の中</code>        | <code>家の中へ行こう</code>   | <code>1</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"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 31 evaluation samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text1                                                                            | text2                                                                            | label                        |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------|
+  | type    | string                                                                           | string                                                                           | int                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 8.39 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.06 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>1: 100.00%</li></ul> |
+* Samples:
+  | text1                 | text2                  | label          |
+  |:----------------------|:-----------------------|:---------------|
+  | <code>花壇</code>       | <code>花壇を調べよう</code>   | <code>1</code> |
+  | <code>タイマツ要らない</code> | <code>キャンドル要らない</code> | <code>1</code> |
+  | <code>なにも要らない</code>  | <code>欲しくない</code>     | <code>1</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`: epoch
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 13
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 8
+- `per_device_eval_batch_size`: 8
+- `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`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 13
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: 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`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch | Step | Training Loss | loss   | custom-arc-semantics-data_max_ap |
+|:-----:|:----:|:-------------:|:------:|:--------------------------------:|
+| None  | 0    | -             | -      | 1.0000                           |
+| 1.0   | 16   | 0.5617        | 0.5022 | 1.0000                           |
+| 2.0   | 32   | 0.2461        | 0.3870 | 1.0000                           |
+| 3.0   | 48   | 0.0968        | 0.3929 | 1.0000                           |
+| 4.0   | 64   | 0.0408        | 0.4012 | 1.0000                           |
+| 5.0   | 80   | 0.0151        | 0.4023 | 1.0000                           |
+| 6.0   | 96   | 0.0118        | 0.3851 | 1.0000                           |
+| 7.0   | 112  | 0.0087        | 0.3637 | 1.0000                           |
+| 8.0   | 128  | 0.0053        | 0.3662 | 1.0000                           |
+| 9.0   | 144  | 0.0046        | 0.3799 | 1.0000                           |
+| 10.0  | 160  | 0.002         | 0.3772 | 1.0000                           |
+| 11.0  | 176  | 0.0025        | 0.3765 | 1.0000                           |
+| 12.0  | 192  | 0.0021        | 0.3751 | 1.0000                           |
+| 13.0  | 208  | 0.0015        | 0.3752 | 1.0000                           |
+
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.0.1
+- Transformers: 4.44.2
+- PyTorch: 2.4.0+cu121
+- Accelerate: 0.34.0
+- Datasets: 2.20.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### 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 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "colorfulscoop/sbert-base-ja",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "cls_token_id": 2,
+  "eos_token_id": 3,
+  "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-12,
+  "mask_token_id": 4,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "sep_token_id": 3,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "unk_token_id": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.44.2",
+    "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 sha256:8fc4e45d599bf652009a700bbe34833cd60aa374b5cc54118f054d6133e99844
+size 442491744

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 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "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:d6467857b4b0c77ded9bac7ad2fb5c16eb64e17e417ce46624dacac2bbb404fc
+size 802713

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": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "<unk>"
+}