Add new SentenceTransformer model

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 +1,400 @@
+---
+base_model: sentence-transformers/all-MiniLM-L6-v2
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:8117
+- loss:CosineSimilarityLoss
+widget:
+- source_sentence: 'Description: I''m looking for a skilled web developer proficient
+    in converting Figma mobile app designs to fully responsive HTML code in Flutter.
+    Key Requirements - Convert Figma designs to HTML, ensuring the output is fully
+    responsive across all devices. - Implement multiple interactive elements as per
+    the original designs. This includes, but is not limited to, sliders and pop-ups.
+    - Utilize clean, efficient code that''s easy to maintain. Ideal Skills and Experience
+    - Extensive experience in Figma to Flutter codeconversion. - Proficient in creating
+    fully responsive web applications. - Strong understanding of interactive web elements.
+    - Exceptional coding skills, with a focus on maintaining code quality and efficiency.'
+  sentences:
+  - 'Skills: Data Entry, eCommerce'
+  - 'Skills: Graphic Design, CSS, HTML, Flutter'
+  - 'Skills: Social Media Marketing, Social Networking, Influencer Marketing, Market
+    Research'
+- source_sentence: 'Description: I''m looking for an experienced C++ developer to
+    help me with a project involving graph data structures. The main focus is implementing
+    the Breadth-First Search BFS traversal algorithm on a graph. Ideal Skills and
+    Experience - Proficient in C++ - Strong understanding of graph data structures
+    - Experience implementing in competitive Programming - Problem-solving skills
+    This project requires not just coding, but also a deep understanding of how graphs
+    work and how to traverse them efficiently using BFS. Please provide examples of
+    similar projects you have completed in the past.'
+  sentences:
+  - 'Skills: C++ Programming, C Programming, Algorithm, Java, C# Programming'
+  - 'Skills: Banner Design, Graphic Design, Animation, Logo Design, Photoshop'
+  - 'Skills: Website Design, Graphic Design, PHP, HTML, User Interface / IA'
+- source_sentence: 'Description: I''m looking for a creative designer to create two
+    engaging, superhero-themed Facebook photos for an ad campaign targeting adults.
+    Key Requirements - Design should be fun and playful, appealing to the target audience
+    - Experience in creating social media visuals and understanding of Facebook''s
+    photo specifications - Skills in graphic design and illustration Ideal Freelancer
+    - Previous experience designing for ad campaigns - Portfolio showcasing playful
+    and fun designs - Understanding of the superhero genre and its appeal to adults'
+  sentences:
+  - 'Skills: Joomla, PHP, C++ Programming, Blueprint Calibration, Floorplan Blueprinting'
+  - 'Skills: Graphic Design, Photoshop, Banner Design, Illustration, Illustrator'
+  - 'Skills: Logo Design, Graphic Design, Illustrator, Photoshop, Icon Design'
+- source_sentence: 'Description: I''m looking for assistance with registering a new
+    Class 2 Digital Signature Certificate DSC for use on the E-filing portal. Ideal
+    Skills and Experience - Proficiency in Digital Signature Certificate DSC registration
+    - Understanding of Class 2 Certificate specifications - Familiarity with E-filing
+    portal requirements and procedures'
+  sentences:
+  - 'Skills: Node.js, Express JS, React.js, SQL, Next.js'
+  - 'Skills: PHP, WordPress, HTML, Website Design, CSS'
+  - 'Skills: Private Client, Digital Marketing, Social Networking'
+- source_sentence: 'Description: I''m seeking an expert in Google Sheets and data
+    management to create a comprehensive tracking system for student progress. Details
+    - Each student will have their own Google Sheet file. - Each file will contain
+    6 levels as separate sheets and a checkbox in each sheet for tracking progress.
+    - When the checkbox is ticked, the data needs to be sent to a central database
+    for us to know the student has completed a level and certificates need to be printed.
+    The data to be sent to the database includes - Student''s Name - Current Level
+    - Package Details - Date and time Ideal skills for this project include - Advanced
+    knowledge of Google Sheets - Experience with data management and database creation
+    - Attention to detail to ensure accurate tracking of each student''s progress.
+    Each student''s Google Sheet should include - Their Name - Their Current Level
+    - Details about the Package they are on - A space to track their Progress Please
+    only apply if you have relevant experience and can demonstrate your ability to
+    deliver this project efficiently.'
+  sentences:
+  - 'Skills: Linux, System Admin, Network Administration, Ubuntu'
+  - 'Skills: PHP, Visual Basic, Data Processing, Data Entry, Excel'
+  - 'Skills: Computer Security, Network Administration, Virtual Machines, Web Security,
+    Linux'
+---
+
+# 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 ea78891063587eb050ed4166b20062eaf978037c -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 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': 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("Nashhz/SBERT_KFOLD_Job_Descriptions_to_Skills")
+# Run inference
+sentences = [
+    "Description: I'm seeking an expert in Google Sheets and data management to create a comprehensive tracking system for student progress. Details - Each student will have their own Google Sheet file. - Each file will contain 6 levels as separate sheets and a checkbox in each sheet for tracking progress. - When the checkbox is ticked, the data needs to be sent to a central database for us to know the student has completed a level and certificates need to be printed. The data to be sent to the database includes - Student's Name - Current Level - Package Details - Date and time Ideal skills for this project include - Advanced knowledge of Google Sheets - Experience with data management and database creation - Attention to detail to ensure accurate tracking of each student's progress. Each student's Google Sheet should include - Their Name - Their Current Level - Details about the Package they are on - A space to track their Progress Please only apply if you have relevant experience and can demonstrate your ability to deliver this project efficiently.",
+    'Skills: PHP, Visual Basic, Data Processing, Data Entry, Excel',
+    'Skills: Computer Security, Network Administration, Virtual Machines, Web Security, Linux',
+]
+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.*
+-->
+
+<!--
+## 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: 8,117 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: 7 tokens</li><li>mean: 139.48 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 16.81 tokens</li><li>max: 33 tokens</li></ul> | <ul><li>min: -0.07</li><li>mean: 0.46</li><li>max: 0.83</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | sentence_1                                                                                        | label                           |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|:--------------------------------|
+  | <code>Description: Looking for a Freelance Videographer & Post-Production Editor! We're hosting a charity event near Sandton, Johannesburg, in support of those affected by abuse. The event will run for about 1-2 hours and features a live band performance. Project Scope Event Recording Capture the entire live set approx. 30 minutes including breaks and speakers, totaling around 1 hour. Post-Production Create a dynamic video for social media, similar to a movie trailer, highlighting the live band and key moments from the event. Photography Take a few impactful photos during the event, including post-production edits. Interviews Film one-on-one segments with speakers for inclusion in the post-event video. Sound Design Incorporate music and sound effects, using creative content available online. Delivery Deadline Edited photos and videos need to be submitted by 14 October 2024. This project aims to capture the spirit of the event, supporting the Family Protection Association login to view URL and empowering women while raising funds and awareness for the cause. If you're interested and have a flair for storytelling through video, please reach out! Date 13 October 2024 Time 1300pm to 1400pm 2 hour set</code> | <code>Skills: Video Editing, Video Production, Video Services, Videography, After Effects</code>  | <code>0.4115103483200073</code> |
+  | <code>Description: Hi! I am Lradon from Andvids. We are a video production agency from China assisting our clients in finding content creators to produce unboxing videos. General requirements of the videos Video duration 1-3 minutes,without music Format Landscape screen 169 MP4 Content â' show your face to explain product features and demonstrate in English fluently. 30 of the time is used to explain product features and show product details, 70 of the time is used to demonstrate the use of the product and the use process in mutiple sences. â'Don't talking about price, personal privacy information, do not appear two-dimensional code, express bill, license plate, door plate, etc Clarity 1080p. Make sure the environment is clean and bright ,and the lens is stable and does not shake Upload to Amazon Sometimes we need you to upload the videos to Amazon If you are interested in this job,feel free to contact me and please send me an introduction video or anything you have shot login to view URL forward to receiving your login to view URL you!</code>                                                                                                                                                                    | <code>Skills: Video Editing, Video Production, Videography, Video Services, After Effects</code>  | <code>0.4927669167518616</code> |
+  | <code>Description: I'm looking for an expert in electronic circuit board design to create and manufacture a simple electronic board for industrial marine machinery. The ideal candidate should have - Experience in designing circuit boards - Ability to design simple, yet effective electronic boards. - Skills in both design and manufacturing of circuit boards. This project is all about creating a reliable, efficient circuit board that can withstand the rigors of marine use. The board is very straight forward design which will be- dc power supply covering 12 volt or 24 volt dc- but range with charging should cover 08 volts to 32 volts dc- it will have an on off button- when selected to on it will engage a 12 vdc solenoid very small and will activate it for 3 minutes and then when stopped it will do this every 7 days on a timer for 3 minutes- when turned off it will not activate and when turned on again it will start again it will activate the solid for 3 minutes and then when finish it will start a 7 day time to repeat the 3 minute solenoid and will be on constant repeat</code>                                                                                                                                     | <code>Skills: Electronics, Electrical Engineering, PCB Layout, Circuit Design, Engineering</code> | <code>0.2869749069213867</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
+
+- `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`: 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
+- `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
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.9843 | 500  | 0.0012        |
+| 1.9685 | 1000 | 0.0011        |
+| 2.9528 | 1500 | 0.0008        |
+| 3.9370 | 2000 | 0.0006        |
+| 0.9843 | 500  | 0.0009        |
+| 1.9685 | 1000 | 0.0008        |
+| 2.9528 | 1500 | 0.0006        |
+| 3.9370 | 2000 | 0.0005        |
+| 0.9843 | 500  | 0.0007        |
+| 1.9685 | 1000 | 0.0007        |
+| 2.9528 | 1500 | 0.0005        |
+| 3.9370 | 2000 | 0.0004        |
+| 0.9843 | 500  | 0.0006        |
+| 1.9685 | 1000 | 0.0006        |
+| 2.9528 | 1500 | 0.0004        |
+| 3.9370 | 2000 | 0.0003        |
+| 0.9843 | 500  | 0.0005        |
+| 1.9685 | 1000 | 0.0005        |
+| 2.9528 | 1500 | 0.0004        |
+| 3.9370 | 2000 | 0.0003        |
+
+
+### Framework Versions
+- Python: 3.12.6
+- Sentence Transformers: 3.2.0
+- Transformers: 4.45.2
+- PyTorch: 2.4.1+cpu
+- Accelerate: 1.0.1
+- Datasets: 3.0.1
+- Tokenizers: 0.20.1
+
+## 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",
+}
+```
+
+<!--
+## 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": "output/SBERT_KFOLD_JD_DnS",
+  "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": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.0",
+    "transformers": "4.45.2",
+    "pytorch": "2.4.1+cpu"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aaf3de6522c4f58ce70420e7b08df65cc746e33a3bcf715dd6390a772245d1c
+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 +1,64 @@
+{
+  "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,
+  "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]"
+}