llama-3-typhoon-v1.5-8b Open-Source Thai Large Language Model - Free Deployment for Thai-English Text Generation

Llama 3 Typhoon V1.5 8b

Developed by scb10x

Typhoon-8B is a Thai large language model with 8 billion parameters built on Llama3-8B, focusing on text generation tasks in Thai and English.

Large Language Model

Transformers

#Thai large model #Pretraining foundation #8 billion parameters

Downloads 4,400

Release Time : 5/6/2024

Model Overview

Typhoon-8B is a Thai large language model that has only undergone pretraining, providing powerful basic capabilities for Thai-related text generation tasks.

Model Features

Thai optimization

Pretrained specifically for Thai, providing more powerful Thai text generation capabilities.

Based on the Llama3 architecture

Built on Meta's Llama3-8B architecture, inheriting its excellent language model characteristics.

Pretrained base model

As a pretrained base model, it can be fine-tuned to adapt to various downstream tasks.

Model Capabilities

Thai text generation

English text generation

Few-shot learning

Use Cases

Natural language processing

Thai text generation

Generate high-quality Thai text content

Language model fine-tuning

Fine-tune for downstream tasks as a base model

🚀 Llama-3-Typhoon-1.5-8B: Thai Large Language Model (Pretrained)

Typhoon-8B is a pretrained only Thai 🇹🇭 large language model with 8 billion parameters, based on Llama3-8B. It aims to provide powerful text - generation capabilities for Thai and English users.

🚀 Quick Start

For release notes, please see our blog. *To acknowledge Meta's effort in creating the foundation model and to comply with the license, we explicitly include "llama-3" in the model name.

✨ Features

Multilingual Support: Supports both Thai 🇹🇭 and English 🇬🇧 languages.
Based on Llama Architecture: Built upon the robust Llama3 - 8B architecture.

📦 Installation

The model requires transformers 4.38.0 or newer. You can install it via the following command:

pip install transformers>=4.38.0

📚 Documentation

Model Description

Property	Details
Model Type	A 8B pretrained decoder - only model based on Llama architecture.
Requirement	transformers 4.38.0 or newer.
Primary Language(s)	Thai 🇹🇭 and English 🇬🇧
License	Llama 3 Community License

Intended Uses & Limitations

This model is a pretrained base model. Thus, it may not be able to follow human instructions without using one/few - shot learning or instruction fine - tuning. The model does not have any moderation mechanisms, and may generate harmful or inappropriate responses.

https://twitter.com/opentyphoon

Support

https://discord.gg/us5gAYmrxw

SCB10X AI Team

Kunat Pipatanakul, Potsawee Manakul, Sittipong Sripaisarnmongkol, Natapong Nitarach, Pathomporn Chokchainant, Kasima Tharnpipitchai
If you find Typhoon - 8B useful for your work, please cite it using:

@article{pipatanakul2023typhoon,
    title={Typhoon: Thai Large Language Models}, 
    author={Kunat Pipatanakul and Phatrasek Jirabovonvisut and Potsawee Manakul and Sittipong Sripaisarnmongkol and Ruangsak Patomwong and Pathomporn Chokchainant and Kasima Tharnpipitchai},
    year={2023},
    journal={arXiv preprint arXiv:2312.13951},
    url={https://arxiv.org/abs/2312.13951}
}

Contact Us

General & Collaboration: kasima@scb10x.com, pathomporn@scb10x.com
Technical: kunat@scb10x.com

📄 License

This model is released under the Llama 3 Community 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