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 +1,407 @@
+---
+base_model: saraleivam/GURU2-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:503
+- loss:SoftmaxLoss
+widget:
+- source_sentence: '#La posición de Ingeniero QA Manual deberá:Priorización de la
+    ejecución de pruebas.Experiencia en la ejecución de pruebas manuales y en la documentación
+    de resultados.Proponer la estrategia de automatización de pruebas y las mejoras
+    a los procesos de automatización.Manejo de plataformas como Atlassian Jira, Atlassian
+    Confluence y GitLab.Conocimiento en motores de bases de datos y lenguajes de programación
+    como .NET, Java, PHP y Python.'
+  sentences:
+  - 'Streamlined Project Management with Trello: AI Integration.Business.Business
+    Essentials.Be able to Initialize and Structure a Go-To-Market Plan Using Trello
+    and AI Tools. Be able to Generate and Organize GTM Strategies Using ChatGPT and
+    Trello. Be able to Enhance GTM Plan Content and Workflow Efficiency with Trello’s
+    AI Tools'
+  - 'Microsoft Power BI Data Analyst.Information Technology.Security.Learn to use
+    Power BI to connect to data sources and transform them into meaningful insights.  .
+    Prepare Excel data for analysis in Power BI using the most common formulas and
+    functions in a worksheet.     . Learn to use the visualization and report capabilities
+    of Power BI to create compelling reports and dashboards.  . Demonstrate your new
+    skills with a capstone project and prepare for the industry-recognized Microsoft
+    PL-300 Certification exam.   '
+  - Getting Started in GIMP.Computer Science.Design and Product.Become Familiar with
+    Using GIMP and GIMPs User Interface. Use Crop and Text Tools. Basic Color Correction
+    Techniques
+- source_sentence: '#La posición de Gerente Jurídico deberá:Apoyar al negocio en la
+    elaboración y revisión y/o negociación de contratos, así como brindar la asesoría
+    y soporte legal en las etapas precontractuales y postcontractuales.Asesorar a
+    la Gerencia General en diversos temas, incluyendo integraciones empresariales.Participar
+    activamente en la toma de decisiones estratégicas para la operación local y en
+    diversos temas en los países a cargo.Asesorar asuntos legales de propiedad intelectual
+    tales como, registros de marcas, patentes y permisos para uso de sustancias y
+    equipos.Fungir como Representante Legal, Apoderado General y Oficial de Cumplimiento
+    de todas las compañías en los países a cargo.Representación de los accionistas
+    extranjeros en juntas y asambleas y/o llevar la secretaría corporativa de la sociedad.Revisar
+    estrategia de respuesta y defensa jurídica en litigios, derechos de petición,
+    tutelas y otras demandas, y asignación de firmas jurídicas externas.Atender y
+    soportar legalmente en las adquisiciones de bienes y servicios de las compañías.Garantizar
+    soporte legal de requerimientos de clientes internos y externos.'
+  sentences:
+  - Data Science.Data Science.Data Analysis.Use R to clean, analyze, and visualize
+    data.. Navigate the entire data science pipeline from data acquisition to publication.
+    . Use GitHub to manage data science projects.. Perform regression analysis, least
+    squares and inference using regression models.
+  - Fundraising and Development Foundations.Business.Business Strategy.Communication,
+    Leadership and Management, Organizational Development, Planning, Strategy, Strategy
+    and Operations, Decision Making, People Development, Prospecting and Qualification,
+    Business Development, Writing
+  - Interfacing with the Arduino.Physical Science and Engineering.Electrical Engineering.Internet
+    Of Things, Computer Programming
+- source_sentence: '#Reportando a Sales Manager ColombiaLograr un crecimiento sostenible
+    de los ingresos mediante la negociación, cierre, implementación y cumplimiento
+    de acuerdos con cuentas clave (usuario final y revendedor).Negociar importantes
+    oportunidades rentables tanto con cuentas clave nuevas como existentes. Experiencia
+    manejando varios países a nivel Latam.Gestionar una cartera de cuentas clave con
+    ingresos totales de 2 a 3 millones de dólares.'
+  sentences:
+  - 'The Blues: Understanding and Performing an American Art Form.Arts and Humanities.Music
+    and Art.Students will be able to describe the blues as an important musical form.
+    . Students will be able to explain differences in jazz and other variations of
+    the blues. '
+  - Managing Employee Performance.Business.Business Essentials.Employee Relations,
+    Human Resources, Leadership and Management, Organizational Development, People
+    Development, People Management, Performance Management, Professional Development,
+    Strategy and Operations, Training, Culture
+  - Marketing on TikTok.Business.Marketing.Social Media, Marketing, Media Strategy
+    & Planning, Strategy, Digital Marketing
+- source_sentence: '#Reportando a la Dirección Comercial. Esta persona sera la responsable
+    de velar por la gestión de las cuentas ya activas y consecución de nuevos clientes
+    en el sector financiero. Su rol principal sera tomar la base instalada de clientes
+    e incrementar el consumo de soluciones que desarrolla la compañía, contribuyendo
+    de esta manera al incremento de ventas para la organización'
+  sentences:
+  - IBM Full Stack Software Developer.Information Technology.Cloud Computing.Master
+    the most up-to-date practical skills and tools that full stack developers use
+    in their daily roles. Learn how to deploy and scale applications using Cloud Native
+    methodologies and tools such as Containers, Kubernetes, Microservices, and Serverless.
+    Develop software with front-end development languages and tools such as HTML,
+    CSS, JavaScript, React, and Bootstrap. Build your GitHub portfolio by applying
+    your skills to multiple labs and hands-on projects, including a capstone
+  - 'Strategising: Management for Global Competitive Advantage.Business.Business Strategy.Analyse
+    how technology and innovation can disrupt and reshape your organisation. Evaluate
+    the different ways supply chains can effectively meet your customer''s demands  .
+    Understand the different  strategies that your organisation can implement in order
+    to remain competitive. Develop your understanding of how organisations can make
+    positive contributions to society while effectively maintaining their bottom line'
+  - Scripting with Python and SQL for Data Engineering.Data Science.Data Analysis.Extract
+    data from different sources and map it to Python data structures.. Design Scripts
+    to connect and query a SQL database from within Python.. Apply scraping techniques
+    to read and extract data from a website.
+- source_sentence: la posición de Ejecutivo Comercial Ingeniero Agrónomo Zootecnista
+    deberá:* Hacer la apertura de mercado en la zona de Caldas.* Hacer las visitas
+    comerciales a los diferentes clientes.
+  sentences:
+  - IBM Full-Stack JavaScript Developer.Computer Science.Software Development.Master
+    the full-stack development languages, frameworks, tools, and technologies to develop
+    job-ready skills valued by employers.. Write, deploy, and scale cloud-native back-end
+    applications using Node, NoSQL databases, containers, microservices, and serverless..
+    Develop websites and front-end software using HTML, CSS, JavaScript, and React..
+    Employ DevOps practices and Agile methodologies to continuously build and deploy
+    software using CI/CD tools.
+  - 'Data Science with Databricks for Data Analysts.Data Science.Data Analysis.Discover
+    how Databricks and Apache Spark simplify big data processing and optimize data
+    analysis. . Frame business problems for data science and machine learning to make
+    the most out of big data analytic workflows.. Solve real-world business problems
+    quickly using Databricks to power the most popular data science techniques. '
+  - 'Power System: Generation, Transmission and Protection.Physical Science and Engineering.Electrical
+    Engineering.Overview of generators and auxiliary system, electrical aspects in
+    a thermal power plant (balance of plants) and related power plant control system.
+    Indian grid scenario, transmission line parameters with real case study, modelling
+    of transmission line parameters using MATLAB. Modern Trends in Electrical Design
+    of EHV, modelling of transmission lines, mechanical design of AC transmission
+    line. Protection system from generation, transmission to distribution including
+    switchgear practical aspects and Gas Insulated Substations'
+---
+
+# SentenceTransformer based on saraleivam/GURU2-paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [saraleivam/GURU2-paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/saraleivam/GURU2-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:** [saraleivam/GURU2-paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/saraleivam/GURU2-paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision a73bbb48c69aae3d4ddfec208a2b666c7f5978c8 -->
+- **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/GURU3-paraphrase-multilingual-MiniLM-L12-v2")
+# Run inference
+sentences = [
+    'la posición de Ejecutivo Comercial Ingeniero Agrónomo Zootecnista deberá:* Hacer la apertura de mercado en la zona de Caldas.* Hacer las visitas comerciales a los diferentes clientes.',
+    'IBM Full-Stack JavaScript Developer.Computer Science.Software Development.Master the full-stack development languages, frameworks, tools, and technologies to develop job-ready skills valued by employers.. Write, deploy, and scale cloud-native back-end applications using Node, NoSQL databases, containers, microservices, and serverless.. Develop websites and front-end software using HTML, CSS, JavaScript, and React.. Employ DevOps practices and Agile methodologies to continuously build and deploy software using CI/CD tools.',
+    'Data Science with Databricks for Data Analysts.Data Science.Data Analysis.Discover how Databricks and Apache Spark simplify big data processing and optimize data analysis. . Frame business problems for data science and machine learning to make the most out of big data analytic workflows.. Solve real-world business problems quickly using Databricks to power the most popular data science techniques. ',
+]
+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: 503 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: 5 tokens</li><li>mean: 87.62 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 16 tokens</li><li>mean: 64.98 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>0: ~73.76%</li><li>1: ~7.75%</li><li>2: ~18.49%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                                                                                                                                     | sentence2                                                                                                                                                                                                                                                                                                                                                             | label          |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Ingenierio electrónico especializado en la implementación de modelos físicos. Experiencia en C++.</code>                                                                                                                                                                | <code>C++ Programming for Unreal Game Development.Computer Science.Software Development.Computer Programming, C Programming Language Family, Computer Programming Tools, Programming Principles</code>                                                                                                                                                                | <code>0</code> |
+  | <code>Analista de datos con años de experiencia. Gran interés hacia el Big Data.</code>                                                                                                                                                                                       | <code>Data Literacy: Exploring and Visualizing Data.Data Science.Data Analysis.Data Analysis, Data Management, Data Visualization, Data Visualization Software, Interactive Data Visualization, SAS (Software), Statistical Visualization, Business Analysis, Data Analysis Software, Exploratory Data Analysis, Statistical Analysis, Statistical Programming</code> | <code>0</code> |
+  | <code>Buscamos profesional en profesional Economía, Administración de empresas, Finanzas con MBA. Mínimo 8 años de experiencia en finanzas corporativas, liderando procesos de levantamiento de deuda, liderando equipos multidisciplinarios. Nivel avanzado de inglés</code> | <code>Advanced Data Modeling.Information Technology.Data Management.Deploy basic data modeling skills and navigate modern storage options for a data warehouse.. Demonstrate data modeling skills within a real-world project environment.</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: 2.3.0+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": "saraleivam/GURU2-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": "2.3.0+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 sha256:51cb75d63066ef3042706a9f7b75e67d474a056871971e5e298b974959647bf9
+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