Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "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 +1,475 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:25310
+- loss:CosineSimilarityLoss
+base_model: Snowflake/snowflake-arctic-embed-s
+widget:
+- source_sentence: encryption algorithms for mobile transactions
+  sentences:
+  - equipaggiamento per sport acquatici
+  - finanziamenti a lungo termine per privati
+  - encryption algorithms for mobile banking
+- source_sentence: tecnologie di liofilizzazione per frutta e verdura
+  sentences:
+  - serbatoi di fermentazione in acciaio inox per cantine
+  - impianti di liofilizzazione per frutta e verdura
+  - medical cannulas
+- source_sentence: servizi di installazione di cavi sottomarini
+  sentences:
+  - servizi di installazione di cavi sottomarini
+  - custom spinal fusion implants
+  - soluzioni disinfettanti per il settore sanitario
+- source_sentence: antifouling paint for yachts
+  sentences:
+  - sistemi di ventilazione con controllo umidità integrato
+  - robot per la movimentazione interna
+  - vernici per automobili
+- source_sentence: materiali isolanti per sistemi radianti a soffitto
+  sentences:
+  - Produzione di contenuti per social media nel settore moda.
+  - privacy and data protection training
+  - materiali isolanti per edifici
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+- cosine_accuracy
+model-index:
+- name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-s
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: custom dataset
+      type: custom_dataset
+    metrics:
+    - type: pearson_cosine
+      value: 0.7037099269944034
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.7286991662955787
+      name: Spearman Cosine
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: all nli dataset
+      type: all_nli_dataset
+    metrics:
+    - type: cosine_accuracy
+      value: 0.8162614107131958
+      name: Cosine Accuracy
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsbenchmark
+      type: stsbenchmark
+    metrics:
+    - type: pearson_cosine
+      value: 0.7477235986007352
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.7431995961099886
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on Snowflake/snowflake-arctic-embed-s
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-s](https://huggingface.co/Snowflake/snowflake-arctic-embed-s). 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:** [Snowflake/snowflake-arctic-embed-s](https://huggingface.co/Snowflake/snowflake-arctic-embed-s) <!-- at revision e596f507467533e48a2e17c007f0e1dacc837b33 -->
+- **Maximum Sequence Length:** 512 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': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("LucaZilli/model-snowflake-s_20250226_145351_finalmodel")
+# Run inference
+sentences = [
+    'materiali isolanti per sistemi radianti a soffitto',
+    'materiali isolanti per edifici',
+    'privacy and data protection training',
+]
+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
+
+* Datasets: `custom_dataset` and `stsbenchmark`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | custom_dataset | stsbenchmark |
+|:--------------------|:---------------|:-------------|
+| pearson_cosine      | 0.7037         | 0.7477       |
+| **spearman_cosine** | **0.7287**     | **0.7432**   |
+
+#### Triplet
+
+* Dataset: `all_nli_dataset`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| **cosine_accuracy** | **0.8163** |
+
+<!--
+## 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: 25,310 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 13.32 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 11.06 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.49</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                        | sentence2                                                           | score            |
+  |:---------------------------------------------------------------------------------|:--------------------------------------------------------------------|:-----------------|
+  | <code>ottimizzazione dei tempi di produzione per capi sartoriali di lusso</code> | <code>strumenti per l'ottimizzazione dei tempi di produzione</code> | <code>0.6</code> |
+  | <code>software di programmazione robotica per lucidatura</code>                  | <code>software gestionale generico</code>                           | <code>0.4</code> |
+  | <code>rete di sensori per l'analisi del suolo in tempo reale</code>              | <code>software per gestione aziendale</code>                        | <code>0.0</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"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 3,164 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 13.61 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 11.39 tokens</li><li>max: 27 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.49</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                             | sentence2                                                                     | score            |
+  |:------------------------------------------------------|:------------------------------------------------------------------------------|:-----------------|
+  | <code>ispezioni regolari per camion aziendali</code>  | <code>ispezioni regolari per camion di consegna</code>                        | <code>1.0</code> |
+  | <code>blister packaging machines GMP compliant</code> | <code>food packaging machines</code>                                          | <code>0.4</code> |
+  | <code>EMI shielding paints for electronics</code>     | <code>Vernici per schermatura elettromagnetica dispositivi elettronici</code> | <code>0.8</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`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 5
+- `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`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `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`: 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`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | custom_dataset_spearman_cosine | all_nli_dataset_cosine_accuracy | stsbenchmark_spearman_cosine |
+|:------:|:----:|:-------------:|:---------------:|:------------------------------:|:-------------------------------:|:----------------------------:|
+| -1     | -1   | -             | -               | 0.7287                         | 0.8163                          | 0.7432                       |
+| 0.1264 | 200  | 0.0671        | 0.0434          | -                              | -                               | -                            |
+| 0.2528 | 400  | 0.0401        | 0.0344          | -                              | -                               | -                            |
+| 0.3793 | 600  | 0.0342        | 0.0307          | -                              | -                               | -                            |
+| 0.5057 | 800  | 0.0347        | 0.0327          | -                              | -                               | -                            |
+| 0.6321 | 1000 | 0.0322        | 0.0287          | -                              | -                               | -                            |
+| 0.7585 | 1200 | 0.032         | 0.0279          | -                              | -                               | -                            |
+| 0.8850 | 1400 | 0.0307        | 0.0282          | -                              | -                               | -                            |
+| 1.0114 | 1600 | 0.0267        | 0.0279          | -                              | -                               | -                            |
+| 1.1378 | 1800 | 0.0244        | 0.0266          | -                              | -                               | -                            |
+| 1.2642 | 2000 | 0.0227        | 0.0282          | -                              | -                               | -                            |
+| 1.3906 | 2200 | 0.0237        | 0.0249          | -                              | -                               | -                            |
+| 1.5171 | 2400 | 0.0222        | 0.0273          | -                              | -                               | -                            |
+| 1.6435 | 2600 | 0.0235        | 0.0246          | -                              | -                               | -                            |
+| 1.7699 | 2800 | 0.0228        | 0.0247          | -                              | -                               | -                            |
+| 1.8963 | 3000 | 0.0225        | 0.0241          | -                              | -                               | -                            |
+| 2.0228 | 3200 | 0.0213        | 0.0244          | -                              | -                               | -                            |
+| 2.1492 | 3400 | 0.0169        | 0.0234          | -                              | -                               | -                            |
+| 2.2756 | 3600 | 0.0178        | 0.0257          | -                              | -                               | -                            |
+| 2.4020 | 3800 | 0.018         | 0.0236          | -                              | -                               | -                            |
+| 2.5284 | 4000 | 0.0177        | 0.0230          | -                              | -                               | -                            |
+| 2.6549 | 4200 | 0.0176        | 0.0234          | -                              | -                               | -                            |
+| 2.7813 | 4400 | 0.0182        | 0.0229          | -                              | -                               | -                            |
+| 2.9077 | 4600 | 0.0173        | 0.0221          | -                              | -                               | -                            |
+| 3.0341 | 4800 | 0.0157        | 0.0232          | -                              | -                               | -                            |
+| 3.1606 | 5000 | 0.0139        | 0.0225          | -                              | -                               | -                            |
+| 3.2870 | 5200 | 0.0137        | 0.0222          | -                              | -                               | -                            |
+| 3.4134 | 5400 | 0.0142        | 0.0224          | -                              | -                               | -                            |
+| 3.5398 | 5600 | 0.0143        | 0.0224          | -                              | -                               | -                            |
+| 3.6662 | 5800 | 0.0135        | 0.0225          | -                              | -                               | -                            |
+| 3.7927 | 6000 | 0.0143        | 0.0223          | -                              | -                               | -                            |
+| 3.9191 | 6200 | 0.0143        | 0.0234          | -                              | -                               | -                            |
+| 4.0455 | 6400 | 0.0128        | 0.0219          | -                              | -                               | -                            |
+| 4.1719 | 6600 | 0.0117        | 0.0222          | -                              | -                               | -                            |
+| 4.2984 | 6800 | 0.0113        | 0.0217          | -                              | -                               | -                            |
+| 4.4248 | 7000 | 0.0115        | 0.0220          | -                              | -                               | -                            |
+| 4.5512 | 7200 | 0.012         | 0.0217          | -                              | -                               | -                            |
+| 4.6776 | 7400 | 0.0113        | 0.0221          | -                              | -                               | -                            |
+| 4.8040 | 7600 | 0.012         | 0.0217          | -                              | -                               | -                            |
+| 4.9305 | 7800 | 0.0105        | 0.0217          | -                              | -                               | -                            |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.48.3
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.3.2
+- 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 +1,25 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/experiments/experiment_model-snowflake-s_20250226_145351/final_model",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,12 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.3",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {
+    "query": "Represent this sentence for searching relevant passages: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b59bdf0c1165a91ff7b12604ddba8bf0e7f26fe72fd1409c520568d5502bfc
+size 133462128

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": 512,
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "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]"
+}