scb10x/typhoon2-qwen2.5-7b

Typhoon2-Qwen2.5-7B: Thai Large Language Model (Instruct)

Typhoon2-Qwen2.5-7B is a pretrained only Thai 🇹🇭 large language model with 7 billion parameters, and it is based on Qwen2.5-7B.

For technical-report. please see our arxiv.

Performance

Model	ThaiExam	ONET	IC	A-Level	TGAT	TPAT	M3Exam	Math	Science	Social	Thai
Typhoon2 Qwen2.5 7B Base	58.86%	58.64%	65.26%	55.11%	66.15%	49.13%	59.90%	42.98%	59.42%	75.62%	61.59%
Qwen2.5 7B	55.74%	51.23%	60.00%	41.73%	72.30%	53.44%	55.65%	46.15%	54.10%	66.54%	55.82%
Typhoon1.5 Llama3 8B Base	48.82%	41.35%	41.05%	40.94%	70.76%	50.00%	43.88%	22.62%	43.47%	62.81%	46.63%

Model Description

• Model type: A 7B decoder-only model based on Qwen2 architecture.
• Requirement: transformers 4.45.0 or newer.
• Primary Language(s): Thai 🇹🇭 and English 🇬🇧
• License: Apache-2.0

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

https://discord.gg/CqyBscMFpg

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}, 
}