Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unigram.json filter=lfs diff=lfs merge=lfs -text

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 +1,393 @@
+---
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+datasets: []
+language: []
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:500
+- loss:SoftmaxLoss
+widget:
+- source_sentence: Reportando a Mánager ventasLograr un crecimiento sostenible de
+    los ingresos mediante la negociación, cierre, implementación y cumplimiento de
+    acuerdos con los diferentes clientes.Encargado de realizar la búsqueda y apertura
+    de nuevos clientes a nivel LATAM . Entender requerimientos y saber asesorar de
+    la mejor manera para un buen cierre de negocio. Alto conocimiento en la línea
+    de flotas y Camiones.
+  sentences:
+  - Modernize Infrastructure and Applications with Google Cloud.Data Science.Business
+    Strategy.Understand the role that cloud modernization and migration plays in an
+    organization's digital transformation.. Examine available options to run compute
+    workloads in the cloud.. Explore the advantages of using containers, serverless
+    computing, and APIs in application modernization.. Learn about the business reasons
+    to choose hybrid or multi-cloud strategies, and how GKE Enterprise can help support
+    these strategies.
+  - Microsoft 365 Copilot for Leaders.Data Science.Machine Learning.Risk Management
+  - 'Decoding AI: A Deep Dive into AI Models and Predictions.Data Science.Machine
+    Learning.Learn key concepts and terminology in artificial intelligence (AI), including
+    machine learning, generative AI, and deep learning . Learn the core components
+    of machine learning systems, including data, models, and evaluation techniques.
+    Recognize why AI systems can fail and identify the kinds of work required to make
+    useful technology. Identify common pitfalls in conversations about AI and recognize
+    conflicts of interest when interpreting claims about AI systems'
+- source_sentence: Reportando a Mánager ventasLograr un crecimiento sostenible de
+    los ingresos mediante la negociación, cierre, implementación y cumplimiento de
+    acuerdos con los diferentes clientes.Encargado de realizar la búsqueda y apertura
+    de nuevos clientes a nivel LATAM . Entender requerimientos y saber asesorar de
+    la mejor manera para un buen cierre de negocio. Alto conocimiento en la línea
+    de flotas y Camiones.
+  sentences:
+  - 'Getting Started with BigQuery Machine Learning.Data Science.Cloud Computing.How
+    to create, evaluate and use machine learning models in BigQuery. '
+  - Convolutional Neural Networks.Data Science.Machine Learning.Artificial Neural
+    Networks, Computer Vision, Machine Learning, Applied Machine Learning, Deep Learning,
+    Machine Learning Software, Machine Learning Algorithms, Network Model, Tensorflow,
+    Network Architecture, Human Learning
+  - 'Understanding Plants - Part II: Fundamentals of Plant Biology.Data Science.Basic
+    Science.Understanding Plants - Part II: Fundamentals of Plant Biology'
+- source_sentence: Reportando a Mánager ventasLograr un crecimiento sostenible de
+    los ingresos mediante la negociación, cierre, implementación y cumplimiento de
+    acuerdos con los diferentes clientes.Encargado de realizar la búsqueda y apertura
+    de nuevos clientes a nivel LATAM . Entender requerimientos y saber asesorar de
+    la mejor manera para un buen cierre de negocio. Alto conocimiento en la línea
+    de flotas y Camiones.
+  sentences:
+  - Introduction to Computer Science and Programming.Data Science.Software Development.1.
+    Use the Javascript language to create interactive programs in the browser with
+    2D graphics.. 2. Convert between number bases, work with modular arithmetic, sequences
+    and series and plot graphs.. 3. Develop and use mental models to describe the
+    workings of a range of computer systems.
+  - Programming Languages, Part A.Data Science.Software Development.Computer Programming,
+    Programming Principles, Algorithms, Critical Thinking
+  - 'Global Health Innovations.Data Science.Public Health.Describe the principles
+    and key types of innovation in order to characterise the fundamental features
+    of new models of care and technologies. Compare and contrast systems that support
+    the development, investment, and protection of healthcare innovation to navigate
+    the innovation journey. Evaluate key factors influencing the adoption and scaling
+    of different healthcare innovations, and examine the reasons why some innovations
+    fail . Critique a particular innovation, using a given framework, in order to
+    make a recommendation to a panel of decision makers. '
+- source_sentence: Reportando a Mánager ventasLograr un crecimiento sostenible de
+    los ingresos mediante la negociación, cierre, implementación y cumplimiento de
+    acuerdos con los diferentes clientes.Encargado de realizar la búsqueda y apertura
+    de nuevos clientes a nivel LATAM . Entender requerimientos y saber asesorar de
+    la mejor manera para un buen cierre de negocio. Alto conocimiento en la línea
+    de flotas y Camiones.
+  sentences:
+  - Development of Secure Embedded Systems.Data Science.Computer Security and Networks.Operating
+    Systems, Systems Design, Computer Programming, System Software, Computer Architecture,
+    Computer Networking, C Programming Language Family, Computer Programming Tools,
+    Hardware Design, Networking Hardware, System Programming, Theoretical Computer
+    Science, Algorithms
+  - GST - Genesis and imposition!.Data Science.Finance.Explain the genesis of GST,
+    the need for its introduction and the Constitutional and legal framework under
+    which it was introduced. .  Identify and describe different forms of supplies
+    of goods and services, deemed supplies and transactions excluded from the scope
+    of supply..  Differentiate various types of supplies and identify whether a supply
+    is inter-State or intra-State, exempt or composite supply..  Critically analyse
+    whether a given transaction is a supply and define the nature of supply.
+  - 'AI for Project Managers and Scrum Masters.Data Science.Business Essentials.Identify
+    key elements of AI for Project Management . Evaluate AI Tools and Techniques for
+    Projects . Integrate AI into Project Lifecycles '
+- source_sentence: Reportando a Mánager ventasLograr un crecimiento sostenible de
+    los ingresos mediante la negociación, cierre, implementación y cumplimiento de
+    acuerdos con los diferentes clientes.Encargado de realizar la búsqueda y apertura
+    de nuevos clientes a nivel LATAM . Entender requerimientos y saber asesorar de
+    la mejor manera para un buen cierre de negocio. Alto conocimiento en la línea
+    de flotas y Camiones.
+  sentences:
+  - Introduction to Data Science and scikit-learn in Python.Data Science.Data Analysis.Employ
+    artificial intelligence techniques to test hypothesis in Python. Apply a machine
+    learning model combining Numpy, Pandas, and Scikit-Learn
+  - 'Planejamento de projetos: Como reunir tudo.Data Science.Leadership and Management.Descrever
+    os componentes da fase de planejamento e a significância deles.. Identificar ferramentas
+    e práticas recomendadas para criar um plano de projeto e um plano de gestão de
+    riscos. . Descrever como estimar, acompanhar e manter um orçamento.. Elaborar
+    um plano de comunicação e explicar como gerenciá-lo.'
+  - Microsoft 365 Copilot for Leaders.Data Science.Machine Learning.Risk Management
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-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/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision bf3bf13ab40c3157080a7ab344c831b9ad18b5eb -->
+- **Maximum Sequence Length:** 128 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': 128, '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})
+)
+```
+
+## 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("saraleivam/GURU-paraphrase-multilingual-MiniLM-L12-v2")
+# Run inference
+sentences = [
+    'Reportando a Mánager ventasLograr un crecimiento sostenible de los ingresos mediante la negociación, cierre, implementación y cumplimiento de acuerdos con los diferentes clientes.Encargado de realizar la búsqueda y apertura de nuevos clientes a nivel LATAM . Entender requerimientos y saber asesorar de la mejor manera para un buen cierre de negocio. Alto conocimiento en la línea de flotas y Camiones.',
+    'Introduction to Data Science and scikit-learn in Python.Data Science.Data Analysis.Employ artificial intelligence techniques to test hypothesis in Python. Apply a machine learning model combining Numpy, Pandas, and Scikit-Learn',
+    'Planejamento de projetos: Como reunir tudo.Data Science.Leadership and Management.Descrever os componentes da fase de planejamento e a significância deles.. Identificar ferramentas e práticas recomendadas para criar um plano de projeto e um plano de gestão de riscos. . Descrever como estimar, acompanhar e manter um orçamento.. Elaborar um plano de comunicação e explicar como gerenciá-lo.',
+]
+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: 500 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                           | label                                                              |
+  |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                              | int                                                                |
+  | details | <ul><li>min: 85 tokens</li><li>mean: 85.0 tokens</li><li>max: 85 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 65.22 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>0: ~10.80%</li><li>1: ~13.20%</li><li>2: ~76.00%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                                                                                                                                                                                                                                                                                       | sentence2                                                                                                                                                                                                                                                                                                                                                                                                                                  | label          |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Reportando a Mánager ventasLograr un crecimiento sostenible de los ingresos mediante la negociación, cierre, implementación y cumplimiento de acuerdos con los diferentes clientes.Encargado de realizar la búsqueda y apertura de nuevos clientes a nivel LATAM . Entender requerimientos y saber asesorar de la mejor manera para un buen cierre de negocio. Alto conocimiento en la línea de flotas y Camiones.</code> | <code>Launching Your Music Career.Data Science.Music and Art.Articulate your Unique Selling Proposition.. Use the Business Model Canvas to determine the core functions required to effectively manage your portfolio career.. Complete a comprehensive growth and recruitment plan for your teaching studio and identify the competitive landscape.. Seek out and book performance opportunities in a variety of settings.</code>         | <code>2</code> |
+  | <code>Reportando a Mánager ventasLograr un crecimiento sostenible de los ingresos mediante la negociación, cierre, implementación y cumplimiento de acuerdos con los diferentes clientes.Encargado de realizar la búsqueda y apertura de nuevos clientes a nivel LATAM . Entender requerimientos y saber asesorar de la mejor manera para un buen cierre de negocio. Alto conocimiento en la línea de flotas y Camiones.</code> | <code>Robotics.Data Science.Electrical Engineering.Motion Planning. Matlab. Estimation</code>                                                                                                                                                                                                                                                                                                                                              | <code>2</code> |
+  | <code>Reportando a Mánager ventasLograr un crecimiento sostenible de los ingresos mediante la negociación, cierre, implementación y cumplimiento de acuerdos con los diferentes clientes.Encargado de realizar la búsqueda y apertura de nuevos clientes a nivel LATAM . Entender requerimientos y saber asesorar de la mejor manera para un buen cierre de negocio. Alto conocimiento en la línea de flotas y Camiones.</code> | <code>Core Java.Data Science.Software Development.Learn the basic syntax and functions of the Java programming language. Apply object-oriented programming techniques to building classes, creating objects, and understanding how solutions are packaged in Java.. Learn how to implement inheritance and polymorphism in Java.. Use selected parts of the vast Java SE class library to enhance your Java programming techniques.</code> | <code>2</code> |
+* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
+
+### Training Hyperparameters
+
+#### 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`: 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
+- `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`: 0.0
+- `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
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.3.1+cu121
+- Accelerate: 0.31.0
+- Datasets: 2.20.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers and SoftmaxLoss
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.3.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cbd1427fc0396967b0b66afacc8b5f1d8f40ccef785dd2429563f721fc98ade
+size 470637416

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "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": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260