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
+}

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 1024, "out_features": 256, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a423884c059d17f3abc05e9b86df67377992f41928843de25136d21b4a9cb17
+size 1049760

README.md

@@ -0,0 +1,459 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:23478
+- loss:ContrastiveLoss
+base_model: denaya/indoSBERT-large
+widget:
+- source_sentence: 'Pekerja anak Indonesia: Buku panduan 2022 (pr & pasca pandemi)'
+  sentences:
+  - Statistik Perusahaan Hak Pengusahaan Hutan 2010
+  - Statistik Kriminal 2016
+  - ' Buletin Statistik Perdagangan Luar Negeri Ekspor Menurut Kelompok Komoditi dan
+    Negara, November 2020'
+- source_sentence: Jumlah pascr tradisional, pusat perbelanjaan, dan toko modern tahun
+    2019
+  sentences:
+  - Profil Pasar Tradisional, Pusat Perbelanjaan, dan Toko Modern 2019
+  - Laporan Perekonomian Indonesia 2008
+  - Profil Industri Mikro dan Kecil 2006
+- source_sentence: Survei biay ahidup (SBH) di Ternate tahun 2012
+  sentences:
+  - Laporan Bulanan Data Sosial Ekonomi Januari 2016
+  - Keadaan Angkatan kerja di Indonesia Agustus 2009
+  - Statistik Perdagangan Luar Negeri Indonesia Impor 2023 Buku I
+- source_sentence: Direktori perwsahaan air minum, listrik, dan gas di kota tahun
+    2009
+  sentences:
+  - Statistik Indonesia 1991
+  - Direktori Perusahaan Air Minum Listrik dan Gas Kota 2009
+  - Direktori Eksportir Indonesia 2015
+- source_sentence: Studi efisiensi industri manufaktr
+  sentences:
+  - Statistik Indonesia 2019
+  - Statistik Potensi Desa Provinsi Maluku 2011
+  - Klasifikasi Baku Komoditas Indonesia (KBKI) 2012 Buku 4
+datasets:
+- yahyaabd/bps-publication-pos-neg-pairs
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on denaya/indoSBERT-large
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: allstats semantic base v1 eval
+      type: allstats-semantic-base-v1-eval
+    metrics:
+    - type: pearson_cosine
+      value: 0.9658815836712943
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.7841756166101173
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: allstat semantic base v1 test
+      type: allstat-semantic-base-v1-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.9592021090962591
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.7818288777895762
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on denaya/indoSBERT-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [denaya/indoSBERT-large](https://huggingface.co/denaya/indoSBERT-large) on the [bps-publication-pos-neg-pairs](https://huggingface.co/datasets/yahyaabd/bps-publication-pos-neg-pairs) dataset. It maps sentences & paragraphs to a 256-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:** [denaya/indoSBERT-large](https://huggingface.co/denaya/indoSBERT-large) <!-- at revision 5c64d43f07f7054dfbf33d226b3066414b6ebc4a -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 256 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [bps-publication-pos-neg-pairs](https://huggingface.co/datasets/yahyaabd/bps-publication-pos-neg-pairs)
+<!-- - **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': 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})
+  (2): Dense({'in_features': 1024, 'out_features': 256, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+)
+```
+
+## 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("yahyaabd/allstats-semantic-base-v1-3")
+# Run inference
+sentences = [
+    'Studi efisiensi industri manufaktr',
+    'Statistik Potensi Desa Provinsi Maluku 2011',
+    'Klasifikasi Baku Komoditas Indonesia (KBKI) 2012 Buku 4',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 256]
+
+# 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
+
+* Datasets: `allstats-semantic-base-v1-eval` and `allstat-semantic-base-v1-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | allstats-semantic-base-v1-eval | allstat-semantic-base-v1-test |
+|:--------------------|:-------------------------------|:------------------------------|
+| pearson_cosine      | 0.9659                         | 0.9592                        |
+| **spearman_cosine** | **0.7842**                     | **0.7818**                    |
+
+<!--
+## 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
+
+#### bps-publication-pos-neg-pairs
+
+* Dataset: [bps-publication-pos-neg-pairs](https://huggingface.co/datasets/yahyaabd/bps-publication-pos-neg-pairs) at [46a5cb7](https://huggingface.co/datasets/yahyaabd/bps-publication-pos-neg-pairs/tree/46a5cb7b0d6b00e9ef6bb1bf0ab6b6628ab66a9b)
+* Size: 23,478 training samples
+* Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                             | doc                                                                               | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 11.84 tokens</li><li>max: 24 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.77 tokens</li><li>max: 28 tokens</li></ul> | <ul><li>0: ~72.40%</li><li>1: ~27.60%</li></ul> |
+* Samples:
+  | query                                                                               | doc                                                                                              | label          |
+  |:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Direktori perusahaan perantara keuangan bukan koperasi tahun 2006 (SE)</code> | <code>Tinjauan Regional Berdasarkan PDRB Kabupaten/Kota 2018-2022, Buku 2 Pulau Jawa-Bali</code> | <code>0</code> |
+  | <code>Informasi lengkap tentang PPLS 2011</code>                                    | <code>Indeks Harga Perdagangan Besar Indonesia tahun 2005</code>                                 | <code>0</code> |
+  | <code>Data konversi GKG ke beras tahun 2012</code>                                  | <code>Indikator Ekonomi Juli 2023</code>                                                         | <code>0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Evaluation Dataset
+
+#### bps-publication-pos-neg-pairs
+
+* Dataset: [bps-publication-pos-neg-pairs](https://huggingface.co/datasets/yahyaabd/bps-publication-pos-neg-pairs) at [46a5cb7](https://huggingface.co/datasets/yahyaabd/bps-publication-pos-neg-pairs/tree/46a5cb7b0d6b00e9ef6bb1bf0ab6b6628ab66a9b)
+* Size: 5,031 evaluation samples
+* Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                             | doc                                                                               | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 11.97 tokens</li><li>max: 24 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.76 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>0: ~72.70%</li><li>1: ~27.30%</li></ul> |
+* Samples:
+  | query                                                                                | doc                                                                                               | label          |
+  |:-------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Informasi angka tanaman berkhasiat ogbat dan tanaman hias di tahun 2005</code> | <code>Tinjauan Regional Berdasarkan PDRB Kabupaten/Kota 2010-2013 - Buku 2 Pulau Jawa-Bali</code> | <code>0</code> |
+  | <code>Informasi lengkap statistik horsikultura tahun 2020</code>                     | <code>NERACA ENERGI INDONESIA 2017-2021</code>                                                    | <code>0</code> |
+  | <code>Statistik air bersih Indonesia periode 2014-2019</code>                        | <code>Profil Usaha Konstruksi Perorangan Provinsi Kalimantan Utara, 2022</code>                   | <code>0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `num_train_epochs`: 8
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `eval_on_start`: True
+
+#### 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`: 64
+- `per_device_eval_batch_size`: 64
+- `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`: 1.0
+- `num_train_epochs`: 8
+- `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`: True
+- `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`: True
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step     | Training Loss | Validation Loss | allstats-semantic-base-v1-eval_spearman_cosine | allstat-semantic-base-v1-test_spearman_cosine |
+|:----------:|:--------:|:-------------:|:---------------:|:----------------------------------------------:|:---------------------------------------------:|
+| 0          | 0        | -             | 0.0053          | 0.7770                                         | -                                             |
+| 0.5450     | 200      | 0.0023        | 0.0005          | 0.7842                                         | -                                             |
+| 1.0899     | 400      | 0.0005        | 0.0002          | 0.7842                                         | -                                             |
+| 1.6349     | 600      | 0.0002        | 0.0002          | 0.7842                                         | -                                             |
+| 2.1798     | 800      | 0.0001        | 0.0001          | 0.7842                                         | -                                             |
+| 2.7248     | 1000     | 0.0001        | 0.0001          | 0.7842                                         | -                                             |
+| 3.2698     | 1200     | 0.0           | 0.0001          | 0.7842                                         | -                                             |
+| 3.8147     | 1400     | 0.0           | 0.0001          | 0.7842                                         | -                                             |
+| 4.3597     | 1600     | 0.0           | 0.0001          | 0.7842                                         | -                                             |
+| **4.9046** | **1800** | **0.0**       | **0.0001**      | **0.7842**                                     | **-**                                         |
+| 5.4496     | 2000     | 0.0           | 0.0001          | 0.7842                                         | -                                             |
+| 5.9946     | 2200     | 0.0           | 0.0001          | 0.7842                                         | -                                             |
+| 6.5395     | 2400     | 0.0           | 0.0001          | 0.7842                                         | -                                             |
+| 7.0845     | 2600     | 0.0           | 0.0001          | 0.7842                                         | -                                             |
+| 7.6294     | 2800     | 0.0           | 0.0001          | 0.7842                                         | -                                             |
+| -1         | -1       | -             | -               | -                                              | 0.7818                                        |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.4.0
+- Transformers: 4.48.1
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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 +1,47 @@
+{
+  "_name_or_path": "denaya/indoSBERT-Large",
+  "_num_labels": 5,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.0",
+    "transformers": "4.48.1",
+    "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 sha256:88349f924d3cbe1fc14f17080cf293d1bc377babae57dc15c9091eaa92731308
+size 1340612432

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_Dense",
+    "type": "sentence_transformers.models.Dense"
+  }
+]

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
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 256,
+  "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]"
+}