Llama3.2-Typhoon2-1B: Thai Large Language Model (Instruct)
Llama3.2-Typhoon2-1B is a pretrained only Thai 🇹🇭 large language model with 1 billion parameters, and it is based on Llama3.2-1B.
For technical-report. please see our arxiv. *To acknowledge Meta's effort in creating the foundation model and to comply with the license, we explicitly include "llama-3.2" in the model name.
Performance
| Model | ThaiExam | ONET | IC | A-Level | TGAT | TPAT | M3Exam | Math | Science | Social | Thai |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Typhoon2 Llama3.2 1B Base | 26.83% | 19.75% | 16.84% | 17.32% | 49.23% | 31.03% | 26.10% | 21.71% | 25.60% | 32.83% | 24.27% |
| Llama3.1 1B | 25.38% | 18.51% | 20.00% | 26.77% | 32.30% | 29.31% | 25.30% | 23.52% | 25.36% | 27.48% | 24.82% |
Model Description
- Model type: A 1B decoder-only model based on Llama architecture.
- Requirement: transformers 4.45.0 or newer.
- Primary Language(s): Thai 🇹🇭 and English 🇬🇧
- License: Llama 3.2 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.
Follow us
https://twitter.com/opentyphoon
Support
Citation
- If you find Typhoon2 useful for your work, please cite it using:
@misc{typhoon2,
title={Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models},
author={Kunat Pipatanakul and Potsawee Manakul and Natapong Nitarach and Warit Sirichotedumrong and Surapon Nonesung and Teetouch Jaknamon and Parinthapat Pengpun and Pittawat Taveekitworachai and Adisai Na-Thalang and Sittipong Sripaisarnmongkol and Krisanapong Jirayoot and Kasima Tharnpipitchai},
year={2024},
eprint={2412.13702},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2412.13702},
}