Delete discipline-model-v3

discipline-model-v3/1_Pooling/config.json

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

discipline-model-v3/README.md

@@ -1,561 +0,0 @@
----
-tags:
-- sentence-transformers
-- sentence-similarity
-- feature-extraction
-- generated_from_trainer
-- dataset_size:5005
-- loss:MultipleNegativesRankingLoss
-base_model: sentence-transformers/all-mpnet-base-v2
-widget:
-- source_sentence: especialista de risco e prevenção a fraudes​
-  sentences:
-  - risk & compliance
-  - internal communication
-  - accounting
-- source_sentence: coord integracao do cliente ii
-  sentences:
-  - strategic planning
-  - customer experience
-  - não encontrado (adicione nas observações)
-- source_sentence: gerente sr. marketing e performance
-  sentences:
-  - business operations
-  - d&i
-  - performance marketing
-- source_sentence: gerente executivo de operacoes
-  sentences:
-  - business operations
-  - sdr
-  - product management
-- source_sentence: sr designer
-  sentences:
-  - product design
-  - talent acquisition
-  - lawyer
-pipeline_tag: sentence-similarity
-library_name: sentence-transformers
-metrics:
-- cosine_accuracy@1
-- cosine_accuracy@3
-- cosine_accuracy@5
-- cosine_accuracy@10
-- cosine_precision@1
-- cosine_precision@3
-- cosine_precision@5
-- cosine_precision@10
-- cosine_recall@1
-- cosine_recall@3
-- cosine_recall@5
-- cosine_recall@10
-- cosine_ndcg@10
-- cosine_mrr@10
-- cosine_map@100
-- dot_accuracy@1
-- dot_accuracy@3
-- dot_accuracy@5
-- dot_accuracy@10
-- dot_precision@1
-- dot_precision@3
-- dot_precision@5
-- dot_precision@10
-- dot_recall@1
-- dot_recall@3
-- dot_recall@5
-- dot_recall@10
-- dot_ndcg@10
-- dot_mrr@10
-- dot_map@100
-model-index:
-- name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: Unknown
-      type: unknown
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.6245583038869258
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.8206713780918727
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.8754416961130742
-      name: Cosine Accuracy@5
-    - type: cosine_accuracy@10
-      value: 0.926678445229682
-      name: Cosine Accuracy@10
-    - type: cosine_precision@1
-      value: 0.6245583038869258
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.2735571260306242
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.17508833922261482
-      name: Cosine Precision@5
-    - type: cosine_precision@10
-      value: 0.0926678445229682
-      name: Cosine Precision@10
-    - type: cosine_recall@1
-      value: 0.6245583038869258
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.8206713780918727
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.8754416961130742
-      name: Cosine Recall@5
-    - type: cosine_recall@10
-      value: 0.926678445229682
-      name: Cosine Recall@10
-    - type: cosine_ndcg@10
-      value: 0.7790196193570564
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@10
-      value: 0.7312496494475299
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.7347864977321262
-      name: Cosine Map@100
-    - type: dot_accuracy@1
-      value: 0.6245583038869258
-      name: Dot Accuracy@1
-    - type: dot_accuracy@3
-      value: 0.8206713780918727
-      name: Dot Accuracy@3
-    - type: dot_accuracy@5
-      value: 0.8754416961130742
-      name: Dot Accuracy@5
-    - type: dot_accuracy@10
-      value: 0.926678445229682
-      name: Dot Accuracy@10
-    - type: dot_precision@1
-      value: 0.6245583038869258
-      name: Dot Precision@1
-    - type: dot_precision@3
-      value: 0.2735571260306242
-      name: Dot Precision@3
-    - type: dot_precision@5
-      value: 0.17508833922261482
-      name: Dot Precision@5
-    - type: dot_precision@10
-      value: 0.0926678445229682
-      name: Dot Precision@10
-    - type: dot_recall@1
-      value: 0.6245583038869258
-      name: Dot Recall@1
-    - type: dot_recall@3
-      value: 0.8206713780918727
-      name: Dot Recall@3
-    - type: dot_recall@5
-      value: 0.8754416961130742
-      name: Dot Recall@5
-    - type: dot_recall@10
-      value: 0.926678445229682
-      name: Dot Recall@10
-    - type: dot_ndcg@10
-      value: 0.7790196193570564
-      name: Dot Ndcg@10
-    - type: dot_mrr@10
-      value: 0.7312496494475299
-      name: Dot Mrr@10
-    - type: dot_map@100
-      value: 0.7347864977321262
-      name: Dot Map@100
----
-
-# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
-
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
-
-## Model Details
-
-### Model Description
-- **Model Type:** Sentence Transformer
-- **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 9a3225965996d404b775526de6dbfe85d3368642 -->
-- **Maximum Sequence Length:** 384 tokens
-- **Output Dimensionality:** 768 tokens
-- **Similarity Function:** Cosine Similarity
-<!-- - **Training Dataset:** Unknown -->
-<!-- - **Language:** Unknown -->
-<!-- - **License:** Unknown -->
-
-### Model Sources
-
-- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
-- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
-- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
-
-### Full Model Architecture
-
-```
-SentenceTransformer(
-  (0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
-  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
-  (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 = [
-    'sr designer',
-    'product design',
-    'talent acquisition',
-]
-embeddings = model.encode(sentences)
-print(embeddings.shape)
-# [3, 768]
-
-# Get the similarity scores for the embeddings
-similarities = model.similarity(embeddings, embeddings)
-print(similarities.shape)
-# [3, 3]
-```
-
-<!--
-### Direct Usage (Transformers)
-
-<details><summary>Click to see the direct usage in Transformers</summary>
-
-</details>
--->
-
-<!--
-### Downstream Usage (Sentence Transformers)
-
-You can finetune this model on your own dataset.
-
-<details><summary>Click to expand</summary>
-
-</details>
--->
-
-<!--
-### Out-of-Scope Use
-
-*List how the model may foreseeably be misused and address what users ought not to do with the model.*
--->
-
-## Evaluation
-
-### Metrics
-
-#### Information Retrieval
-
-* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
-
-| Metric              | Value      |
-|:--------------------|:-----------|
-| cosine_accuracy@1   | 0.6246     |
-| cosine_accuracy@3   | 0.8207     |
-| cosine_accuracy@5   | 0.8754     |
-| cosine_accuracy@10  | 0.9267     |
-| cosine_precision@1  | 0.6246     |
-| cosine_precision@3  | 0.2736     |
-| cosine_precision@5  | 0.1751     |
-| cosine_precision@10 | 0.0927     |
-| cosine_recall@1     | 0.6246     |
-| cosine_recall@3     | 0.8207     |
-| cosine_recall@5     | 0.8754     |
-| cosine_recall@10    | 0.9267     |
-| cosine_ndcg@10      | 0.779      |
-| cosine_mrr@10       | 0.7312     |
-| **cosine_map@100**  | **0.7348** |
-| dot_accuracy@1      | 0.6246     |
-| dot_accuracy@3      | 0.8207     |
-| dot_accuracy@5      | 0.8754     |
-| dot_accuracy@10     | 0.9267     |
-| dot_precision@1     | 0.6246     |
-| dot_precision@3     | 0.2736     |
-| dot_precision@5     | 0.1751     |
-| dot_precision@10    | 0.0927     |
-| dot_recall@1        | 0.6246     |
-| dot_recall@3        | 0.8207     |
-| dot_recall@5        | 0.8754     |
-| dot_recall@10       | 0.9267     |
-| dot_ndcg@10         | 0.779      |
-| dot_mrr@10          | 0.7312     |
-| dot_map@100         | 0.7348     |
-
-<!--
-## 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: 5,005 training samples
-* Columns: <code>input</code> and <code>output</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | input                                                                            | output                                                                           |
-  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
-  | type    | string                                                                           | string                                                                           |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 8.83 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.21 tokens</li><li>max: 18 tokens</li></ul> |
-* Samples:
-  | input                                       | output                                                 |
-  |:--------------------------------------------|:-------------------------------------------------------|
-  | <code>fresador mecanico ii</code>           | <code>não encontrado (adicione nas observações)</code> |
-  | <code>analista de sistemas ui ux iii</code> | <code>product design</code>                            |
-  | <code>devops</code>                         | <code>devops engineering</code>                        |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
-  ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
-  ```
-
-### Evaluation Dataset
-
-#### Unnamed Dataset
-
-
-* Size: 1,132 evaluation samples
-* Columns: <code>input</code> and <code>output</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | input                                                                            | output                                                                           |
-  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
-  | type    | string                                                                           | string                                                                           |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 8.76 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.08 tokens</li><li>max: 18 tokens</li></ul> |
-* Samples:
-  | input                                    | output                                                 |
-  |:-----------------------------------------|:-------------------------------------------------------|
-  | <code>produtor (a) de video pleno</code> | <code>não encontrado (adicione nas observações)</code> |
-  | <code>ai staff software engineer</code>  | <code>software engineering</code>                      |
-  | <code>montador digital i</code>          | <code>não encontrado (adicione nas observações)</code> |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
-  ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
-  ```
-
-### Training Hyperparameters
-#### Non-Default Hyperparameters
-
-- `eval_strategy`: steps
-- `warmup_ratio`: 0.1
-
-#### 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`: 8
-- `per_device_eval_batch_size`: 8
-- `per_gpu_train_batch_size`: None
-- `per_gpu_eval_batch_size`: None
-- `gradient_accumulation_steps`: 1
-- `eval_accumulation_steps`: None
-- `torch_empty_cache_steps`: None
-- `learning_rate`: 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`: 3.0
-- `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`: 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`: proportional
-
-</details>
-
-### Training Logs
-| Epoch  | Step | Training Loss | loss   | cosine_map@100 |
-|:------:|:----:|:-------------:|:------:|:--------------:|
-| 0      | 0    | -             | -      | 0.3578         |
-| 0.3195 | 200  | -             | 0.9975 | 0.5035         |
-| 0.6390 | 400  | -             | 0.8471 | 0.5845         |
-| 0.7987 | 500  | 1.0355        | -      | -              |
-| 0.9585 | 600  | -             | 0.7569 | 0.6157         |
-| 1.2780 | 800  | -             | 0.7542 | 0.6565         |
-| 1.5974 | 1000 | 0.648         | 0.6835 | 0.6786         |
-| 1.9169 | 1200 | -             | 0.6569 | 0.6851         |
-| 2.2364 | 1400 | -             | 0.6480 | 0.7167         |
-| 2.3962 | 1500 | 0.5253        | -      | -              |
-| 2.5559 | 1600 | -             | 0.6506 | 0.7110         |
-| 2.8754 | 1800 | -             | 0.6391 | 0.7348         |
-
-
-### Framework Versions
-- Python: 3.11.6
-- Sentence Transformers: 3.1.1
-- Transformers: 4.45.2
-- PyTorch: 2.5.1+cu124
-- Accelerate: 1.1.1
-- Datasets: 2.14.4
-- Tokenizers: 0.20.3
-
-## Citation
-
-### BibTeX
-
-#### Sentence Transformers
-```bibtex
-@inproceedings{reimers-2019-sentence-bert,
-    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
-    author = "Reimers, Nils and Gurevych, Iryna",
-    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
-    month = "11",
-    year = "2019",
-    publisher = "Association for Computational Linguistics",
-    url = "https://arxiv.org/abs/1908.10084",
-}
-```
-
-#### MultipleNegativesRankingLoss
-```bibtex
-@misc{henderson2017efficient,
-    title={Efficient Natural Language Response Suggestion for Smart Reply},
-    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
-    year={2017},
-    eprint={1705.00652},
-    archivePrefix={arXiv},
-    primaryClass={cs.CL}
-}
-```
-
-<!--
-## Glossary
-
-*Clearly define terms in order to be accessible across audiences.*
--->
-
-<!--
-## Model Card Authors
-
-*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
--->
-
-<!--
-## Model Card Contact
-
-*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--->

discipline-model-v3/config.json

@@ -1,24 +0,0 @@
-{
-  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
-  "architectures": [
-    "MPNetModel"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "mpnet",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "relative_attention_num_buckets": 32,
-  "torch_dtype": "float32",
-  "transformers_version": "4.45.2",
-  "vocab_size": 30527
-}

discipline-model-v3/config_sentence_transformers.json

@@ -1,10 +0,0 @@
-{
-  "__version__": {
-    "sentence_transformers": "3.1.1",
-    "transformers": "4.45.2",
-    "pytorch": "2.5.1+cu124"
-  },
-  "prompts": {},
-  "default_prompt_name": null,
-  "similarity_fn_name": null
-}

discipline-model-v3/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b5855a55cd3835eec991b1c6b1d902581ed783c5a6ac097472f3296a3e642cc6
-size 437967672

discipline-model-v3/modules.json

@@ -1,20 +0,0 @@
-[
-  {
-    "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"
-  }
-]

discipline-model-v3/sentence_bert_config.json

@@ -1,4 +0,0 @@
-{
-  "max_seq_length": 384,
-  "do_lower_case": false
-}

discipline-model-v3/special_tokens_map.json

@@ -1,51 +0,0 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

discipline-model-v3/tokenizer_config.json

@@ -1,72 +0,0 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "104": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "30526": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "cls_token": "<s>",
-  "do_lower_case": true,
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "max_length": 128,
-  "model_max_length": 384,
-  "pad_to_multiple_of": null,
-  "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "sep_token": "</s>",
-  "stride": 0,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "MPNetTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "[UNK]"
-}