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 +1,378 @@
+---
+base_model: saraleivam/GURU-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: Servicio consultor SAP MM con experiencia Data Maestra SemiSenior,
+ actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP
+ Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni
+ a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.
+ sentences:
+ - Data mining of Clinical Databases - CDSS 1.Data Science.Machine Learning.Understand
+ the Schema of publicly available EHR databases (MIMIC-III). Recognise the International
+ Classification of Diseases (ICD) use. Extract and visualise descriptive statistics
+ from clinical databases. Understand and extract key clinical outcomes such as
+ mortality and stay of length
+ - Natural Language Processing on Google Cloud.Data Science.Machine Learning.Machine
+ Learning, Natural Language Processing, Tensorflow
+ - 'Auditing I: Conceptual Foundations of Auditing.Business.Business Essentials.Accounting,
+ Audit, Critical Thinking, Financial Analysis, Regulations and Compliance, Risk
+ Management, Financial Accounting, General Accounting, Leadership and Management,
+ Finance'
+- source_sentence: Servicio consultor SAP MM con experiencia Data Maestra SemiSenior,
+ actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP
+ Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni
+ a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.
+ sentences:
+ - Generando modelos con Auto Machine Learning.Data Science.Machine Learning.Desarrollar
+ modelos utilizando herramientas de Auto Machine Learning. Explorar los datos y
+ hacer el tratamiento para su uso al generar modelos
+ - Professionalism in Allied Health.Personal Development.Personal Development.Gain
+ an understanding of the expectations of an allied healthcare professional in the
+ workplace. Develop and exercise emotional intelligence, self-management, and interpersonal
+ skills. Build and improve internal and external communication skills with all
+ exchanges. Enhance the patient care experience with successful interactions and
+ patient satisfaction
+ - Big Data, Genes, and Medicine.Health.Health Informatics.Big Data, Bioinformatics,
+ Data Analysis, Data Analysis Software, Statistical Programming, Algorithms, Exploratory
+ Data Analysis, Computer Programming
+- source_sentence: Servicio consultor SAP MM con experiencia Data Maestra SemiSenior,
+ actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP
+ Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni
+ a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.
+ sentences:
+ - Retail Marketing Strategy.Business.Marketing.Brand Management, Leadership and
+ Management, Marketing, Sales, Strategy, Strategy and Operations, Retail Sales,
+ Retail Store Operations, Data Analysis, E-Commerce
+ - Supporting Veteran Success in Higher Education.Personal Development.Personal Development.Supporting
+ Veteran Success in Higher Education
+ - Advanced AI Techniques for the Supply Chain.Data Science.Machine Learning.Machine
+ Learning, Natural Language Processing
+- source_sentence: Servicio consultor SAP MM con experiencia Data Maestra SemiSenior,
+ actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP
+ Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni
+ a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.
+ sentences:
+ - Fundamentals of Flight mechanics.Physical Science and Engineering.Physics and
+ Astronomy.How Mach number can impact stall speed.. Why turboprops consume less
+ than turbojets.. What exactly mean indications given by flight instruments (i.e.
+ anemometer, altimeter).
+ - 'Learn English: Beginning Grammar.Language Learning.Learning English.Writing,
+ Communication'
+ - Product Management Certification.Business.Leadership and Management.Apply key
+ product management skills, tools, and techniques to engage and manage key stakeholders
+ and clients. Identify product strategy development and implementation methods
+ and best practices to ensure the right product is produced. Describe product development
+ and analysis best practices to effectively manage change and ensure a successful
+ product launch. Test what you have learned in a series of practical exercises
+ allowing you to demonstrate real-word product management
+- source_sentence: Servicio consultor SAP MM con experiencia Data Maestra SemiSenior,
+ actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP
+ Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni
+ a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.
+ sentences:
+ - 'Python, Bash and SQL Essentials for Data Engineering.Computer Science.Software
+ Development.Develop data engineering solutions with a minimal and essential subset
+ of the Python language and the Linux environment. Design scripts to connect and
+ query a SQL database using Python. Use a scraping library in Python to read, identify
+ and extract data from websites '
+ - 'AI-Enhanced Content Creation:Elevate Copywriting with Humata.Data Science.Machine
+ Learning.Use prompts in Humata AI to get the information needed to generate an
+ ad copy from the source files. . Create engaging ads and blog posts tailored
+ to your audience with the help of Humata AI prompts. . Create a compelling advertisement
+ for various online platforms using prompt engineering in Humata AI. '
+ - SQL for Data Science Capstone Project.Data Science.Data Analysis.Develop a project
+ proposal and select your data. Perform descriptive statistics as part of your
+ exploratory analysis. Develop metrics and perform advanced techniques in SQL.
+ Present your findings and make recommendations
+---
+
+# SentenceTransformer based on saraleivam/GURU-paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [saraleivam/GURU-paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/saraleivam/GURU-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/GURU-paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/saraleivam/GURU-paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 0f16d34e08fc583b71c922dc18d3b14eba17983c -->
+- **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/GURU2-paraphrase-multilingual-MiniLM-L12-v2")
+# Run inference
+sentences = [
+ 'Servicio consultor SAP MM con experiencia Data Maestra SemiSenior, actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.',
+ 'Python, Bash and SQL Essentials for Data Engineering.Computer Science.Software Development.Develop data engineering solutions with a minimal and essential subset of the Python language and the Linux environment. Design scripts to connect and query a SQL database using Python. Use a scraping library in Python to read, identify and extract data from websites ',
+ 'AI-Enhanced Content Creation:Elevate Copywriting with Humata.Data Science.Machine Learning.Use prompts in Humata AI to get the information needed to generate an ad copy from the source files. . Create engaging ads and blog posts tailored to your audience with the help of Humata AI prompts. . Create a compelling advertisement for various online platforms using prompt engineering in Humata AI. ',
+]
+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: 77 tokens</li><li>mean: 77.0 tokens</li><li>max: 77 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 64.05 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>0: ~17.00%</li><li>1: ~25.00%</li><li>2: ~58.00%</li></ul> |
+* Samples:
+ | sentence1 | sentence2 | label |
+ |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+ | <code>Servicio consultor SAP MM con experiencia Data Maestra SemiSenior, actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.</code> | <code>Introduction to Generative AI - 한국어.Information Technology.Cloud Computing.생성형 AI 정의. 생성형 AI의 작동 방식 설명. 생성형 AI 모델 유형 설명. 생성형 AI 애플리케이션 설명</code> | <code>0</code> |
+ | <code>Servicio consultor SAP MM con experiencia Data Maestra SemiSenior, actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.</code> | <code>Mastering Excel Essentials to Enhance Business Value.Business.Business Essentials.Effectively input data and efficiently navigate large spreadsheets.. Employ various "hacks" and expertly apply (the most appropriate) built-in functions in Excel to increase productivity and streamline workflow.. Apply the "what-if" analysis tools in Excel to conduct break-even analysis, conduct sensitivity analysis and support decision-making.</code> | <code>1</code> |
+ | <code>Servicio consultor SAP MM con experiencia Data Maestra SemiSenior, actualizaciones, referencias, ingles B2, remoto. Que maneje plantillas de SAP Bridge e Ibérico. Con experiencia en ServiceNow. No llegan ni a implementar, ni a ejecutar ni a hacer roll out. Llega a enfocarse en 30% en master data.</code> | <code>Exploring Piano Literature: The Piano Sonata.Arts and Humanities.Music and Art.Identify specific historical time periods in which the popularity of sonatas increases or decreases and the reasons behind these trends. . Identify sonata form. Recognize the most influential pieces in the sonata repertoire. </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": "saraleivam/GURU-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 sha256:5869581ff3810f2393f52047ad7e7a0ec2e64419bedb5e3411bd04f4f6ef8055
+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