IndoBERT-large-p2 Open-source Indonesian Language Model - Empowering Indonesian Content Understanding and Processing

Indobert Large P2

Developed by indobenchmark

IndoBERT is a state-of-the-art language model developed for Indonesian based on the BERT architecture, trained using Masked Language Modeling (MLM) and Next Sentence Prediction (NSP) objectives.

Large Language Model OtherOpen Source License:MIT #Indonesian Pretraining #Case Insensitive #Multi-task Learning

Downloads 2,272

Release Time : 3/2/2022

Model Overview

IndoBERT is a pre-trained language model optimized for Indonesian, primarily used for natural language understanding tasks, supporting contextual representation extraction and language comprehension for Indonesian text.

Model Features

Indonesian Optimization

Specifically optimized for Indonesian, suitable for natural language processing tasks in Indonesian.

Large-scale Pretraining

Pretrained on the Indo4B dataset (23.43 GB of text), offering robust language understanding capabilities.

Case Insensitive

The model does not distinguish between uppercase and lowercase during the second phase of training, making it suitable for text inputs with varying cases.

Model Capabilities

Indonesian Text Understanding

Contextual Representation Extraction

Masked Language Modeling

Next Sentence Prediction

Use Cases

Natural Language Processing

Text Classification

Used for classification tasks in Indonesian text, such as sentiment analysis, topic classification, etc.

Named Entity Recognition

Identifies named entities in Indonesian text, such as person names, locations, organization names, etc.

Language Model Fine-tuning

Downstream Task Fine-tuning

Can be fine-tuned to adapt to specific Indonesian NLP tasks.

🚀 IndoBERT Large Model (phase2 - uncased)

IndoBERT is a state - of - the - art language model for Indonesian, built upon the BERT model. It is pretrained using masked language modeling (MLM) and next sentence prediction (NSP) objectives, offering high - quality language understanding capabilities for the Indonesian language.

🚀 Quick Start

Load model and tokenizer

from transformers import BertTokenizer, AutoModel
tokenizer = BertTokenizer.from_pretrained("indobenchmark/indobert-large-p2")
model = AutoModel.from_pretrained("indobenchmark/indobert-large-p2")

Extract contextual representation

x = torch.LongTensor(tokenizer.encode('aku adalah anak [MASK]')).view(1,-1)
print(x, model(x)[0].sum())

✨ Features

All Pre - trained Models

Property	Details
Model Type	`indobenchmark/indobert-base-p1`, `indobenchmark/indobert-base-p2`, `indobenchmark/indobert-large-p1`, `indobenchmark/indobert-large-p2`, `indobenchmark/indobert-lite-base-p1`, `indobenchmark/indobert-lite-base-p2`, `indobenchmark/indobert-lite-large-p1`, `indobenchmark/indobert-lite-large-p2`
Training Data	Indo4B (23.43 GB of text)
#params	124.5M (Base models), 335.2M (Large models), 11.7M (Lite Base models), 17.7M (Lite Large models)
Arch.	Base, Large

📚 Documentation

Authors

IndoBERT was trained and evaluated by Bryan Wilie*, Karissa Vincentio*, Genta Indra Winata*, Samuel Cahyawijaya*, Xiaohong Li, Zhi Yuan Lim, Sidik Soleman, Rahmad Mahendra, Pascale Fung, Syafri Bahar, Ayu Purwarianti.

Citation

If you use our work, please cite:

@inproceedings{wilie2020indonlu,
  title={IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding},
  author={Bryan Wilie and Karissa Vincentio and Genta Indra Winata and Samuel Cahyawijaya and X. Li and Zhi Yuan Lim and S. Soleman and R. Mahendra and Pascale Fung and Syafri Bahar and A. Purwarianti},
  booktitle={Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing},
  year={2020}
}

📄 License

This project is licensed under the MIT license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご