Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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 +1,441 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:7022
+- loss:CosineSimilarityLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: nike indigo man presents an invigorating blend that captures the
+    essence of modern masculinity with a fresh and woody character launched in 2015
+    this fragrance seamlessly weaves together vibrant citrus notes and aromatic spices
+    offering an energizing experience that is both elegant and bold users describe
+    it as sophisticated yet approachable making it perfect for daily wear or special
+    occasions the fragrance elicits feelings of confidence and freshness with many
+    appreciating its unique combination of floral nuances balanced by warm earthy
+    undertones reviewers frequently note its impressively longlasting quality allowing
+    its captivating scent to linger throughout the day with a solid rating of 388
+    nike indigo man is lauded not only for its wellrounded olfactory profile but also
+    for its ability to leave a lasting impression embodying both vigor and refinement
+  sentences:
+  - ozonic notes
+  - cedar
+  - earthy notes
+- source_sentence: nike indigo man presents an invigorating blend that captures the
+    essence of modern masculinity with a fresh and woody character launched in 2015
+    this fragrance seamlessly weaves together vibrant citrus notes and aromatic spices
+    offering an energizing experience that is both elegant and bold users describe
+    it as sophisticated yet approachable making it perfect for daily wear or special
+    occasions the fragrance elicits feelings of confidence and freshness with many
+    appreciating its unique combination of floral nuances balanced by warm earthy
+    undertones reviewers frequently note its impressively longlasting quality allowing
+    its captivating scent to linger throughout the day with a solid rating of 388
+    nike indigo man is lauded not only for its wellrounded olfactory profile but also
+    for its ability to leave a lasting impression embodying both vigor and refinement
+  sentences:
+  - amber
+  - cypress
+  - ivy
+- source_sentence: named after the novel of the same name by poet and aviator antoine
+    de saintexupery the perfume is a tribute to women who like to take risks
+  sentences:
+  - pear
+  - fruity notes
+  - woody notes
+- source_sentence: basi femme by armand basi exudes a playful yet sophisticated charm
+    that captures the essence of femininity launched in 2000 this fragrance envelops
+    wearers in a delightful bouquet of floral and fruity elements balanced by warm
+    and comforting undertones users describe it as sweet and aromatic with hints of
+    soft spice that create a captivating allure the scent is often praised for its
+    versatility making it suitable for both day and evening wear feedback highlights
+    its elegance and freshness which evoke a sense of confidence and joy many appreciate
+    its soft yet distinct presence noting how it leaves a lasting impression without
+    overwhelming the senses the overall mood is uplifting and approachable perfect
+    for the modern woman who seeks to express her individuality while remaining effortlessly
+    chic with a solid rating from its community basi femme resonates as a timeless
+    fragrance choice celebrated for its inviting and warm character
+  sentences:
+  - citrus notes
+  - fig leaf
+  - jasmine petal
+- source_sentence: lalibela by memo paris is an enchanting fragrance that transports
+    you to a lush garden awash with the vibrancy of blooming flowers this scent harmoniously
+    blends rich floral notes with a warm sweet undertone creating a captivating atmosphere
+    that feels both opulent and inviting the essence of tender blooms is beautifully
+    complemented by a hint of creamy sweetness enveloping the wearer in a soft and
+    sensuous embrace users describe lalibela as a sophisticated and luxurious perfume
+    often noting its unique complexity that unfolds throughout the day with a cozy
+    warmth reminiscent of cherished memories it evokes feelings of comfort and elegance
+    many appreciate its longlasting presence making it a favorite for both day and
+    evening wear reviewers highlight the fragrances ability to turn heads leaving
+    a memorable impression without being overwhelming overall lalibela is a masterful
+    olfactory experience that embodies the spirit of femininity perfect for those
+    seeking a signature scent infused with both richness and charm
+  sentences:
+  - vanilla
+  - cypress
+  - green notes
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: pearson_cosine
+      value: 0.9221809753640012
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8309208495457832
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-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/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision fa97f6e7cb1a59073dff9e6b13e2715cf7475ac9 -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 dimensions
+- **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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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 = [
+    'lalibela by memo paris is an enchanting fragrance that transports you to a lush garden awash with the vibrancy of blooming flowers this scent harmoniously blends rich floral notes with a warm sweet undertone creating a captivating atmosphere that feels both opulent and inviting the essence of tender blooms is beautifully complemented by a hint of creamy sweetness enveloping the wearer in a soft and sensuous embrace users describe lalibela as a sophisticated and luxurious perfume often noting its unique complexity that unfolds throughout the day with a cozy warmth reminiscent of cherished memories it evokes feelings of comfort and elegance many appreciate its longlasting presence making it a favorite for both day and evening wear reviewers highlight the fragrances ability to turn heads leaving a memorable impression without being overwhelming overall lalibela is a masterful olfactory experience that embodies the spirit of femininity perfect for those seeking a signature scent infused with both richness and charm',
+    'vanilla',
+    'green notes',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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
+
+#### Semantic Similarity
+
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.9222     |
+| **spearman_cosine** | **0.8309** |
+
+<!--
+## 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: 7,022 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                           | sentence_1                                                                      | label                                                          |
+  |:--------|:-------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                               | string                                                                          | float                                                          |
+  | details | <ul><li>min: 12 tokens</li><li>mean: 178.91 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.93 tokens</li><li>max: 7 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.51</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | sentence_1                | label            |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------|:-----------------|
+  | <code>americas by mahogany is an invigorating fragrance crafted for the modern man embodying the spirit of adventure and exploration this scent opens with a refreshing burst that hints at invigorating elements balanced with a spicy warmth that captivates the senses users often describe it as a harmonious blend of fresh and woody accords creating an atmosphere that is both vibrant and grounding this perfumes unique composition has garnered praise for its longevity and versatility making it suitable for both day and evening wear reviewers highlight its ability to evoke a sense of confidence and sophistication likening its character to a breezy stroll through verdant landscapes complemented by hints of rich aromatic woods the overall mood is one of refined masculinity inviting wearers to embrace their individuality while leaving a memorable impression with a commendable rating of 426 out of 5 americas resonates with those seeking a fragrance that is fresh yet complex encapsulating the essence o...</code> | <code>black pepper</code> | <code>1.0</code> |
+  | <code>rosa gallica by brecourt is an exquisite unisex fragrance that encapsulates a warm and inviting aura perfect for those who appreciate the elegance of nature intertwined with a touch of mystique with its alluring blend of floral and woody elements this fragrance wraps the wearer in a soft balsamic embrace that evokes a sense of serene sophistication crafted by renowned perfumer emilie bouge rosa gallica has garnered a favorable reception from users who describe it as both captivating and refined reviewers often highlight its unique combination of spicy warmth and delicate floral notes creating an atmosphere that is both romantic and grounded its celebrated for its longevity allowing the wearer to carry its gentle yet complex character throughout the day fans of this fragrance appreciate its versatility noting it as suitable for both day and evening wear with many finding it perfect for cooler weather the overall sentiment points to a fragrance that feels timeless and elegant evoking the...</code> | <code>pimento</code>      | <code>0.0</code> |
+  | <code>roberto cavalli nero assoluto is a mesmerizing fragrance that embodies a rich and sensual experience perfect for the confident modern woman with its intriguing blend of velvety florals and warm undertones this perfume radiates an aura of elegance and sophistication users frequently describe it as both alluring and comforting invoking sensations of nightfall enhanced by an embrace of soft sweetness the fragrance opens with captivating floral notes that invite curiosity and provide a fresh inviting introduction as it evolves deeper and warmer accords emerge creating a luxurious complexity that many wearers find addictive the interplay between the sweet and powdery elements gives it a creamy enveloping quality that makes it an excellent choice for evening wear or special occasions with an impressive rating from fragrance enthusiasts many reviewers appreciate its longevity and sillage stating that it lingers beautifully without being overpowering the overall impression of nero assoluto is ...</code> | <code>blonde woods</code> | <code>1.0</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `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`: 32
+- `per_device_eval_batch_size`: 32
+- `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`: None
+- `hub_always_push`: False
+- `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
+- `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
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | spearman_cosine |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.2273 | 50   | -             | 0.2856          |
+| 0.4545 | 100  | -             | 0.7237          |
+| 0.6818 | 150  | -             | 0.7814          |
+| 0.9091 | 200  | -             | 0.8037          |
+| 1.0    | 220  | -             | 0.8096          |
+| 1.1364 | 250  | -             | 0.8067          |
+| 1.3636 | 300  | -             | 0.8130          |
+| 1.5909 | 350  | -             | 0.8195          |
+| 1.8182 | 400  | -             | 0.8221          |
+| 2.0    | 440  | -             | 0.8222          |
+| 2.0455 | 450  | -             | 0.8229          |
+| 2.2727 | 500  | 0.0988        | 0.8177          |
+| 2.5    | 550  | -             | 0.8277          |
+| 2.7273 | 600  | -             | 0.8273          |
+| 2.9545 | 650  | -             | 0.8287          |
+| 3.0    | 660  | -             | 0.8287          |
+| 3.1818 | 700  | -             | 0.8269          |
+| 3.4091 | 750  | -             | 0.8295          |
+| 3.6364 | 800  | -             | 0.8301          |
+| 3.8636 | 850  | -             | 0.8306          |
+| 4.0    | 880  | -             | 0.8309          |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.3.1
+- Transformers: 4.47.1
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.2.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## 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",
+}
+```
+
+<!--
+## 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 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.47.1",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a4a09e046c9d294c5abfe2256b727f4fc75eddd4ad5f8736c245b5cab3f1519
+size 90864192

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
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}