5,327,456 AI resources indexedWorking toward the world’s largest AI resource index.

Browse resources 12 sections
PDF

Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models

This paper introduces Typhoon 2, a series of text and multimodal large language models optimized for the Thai language. The series includes models for text, vision, and audio. Typhoon2-Text builds on state-of-the-art open models, such as Llama 3 and Qwen2, and we perform continual pre-training on a mixture of English and Thai data. We employ post-training techniques to enhance Thai language performance while preserving the base models' original capabilities. We release text models across a range of sizes, from 1 to 70 billion parameters, available in both base and instruction-tuned variants. To guardrail text generation, we release Typhoon2-S

By Pipatanakul, Kunat, Manakul, Potsawee, Nitarach, Natapong, Sirichotedumrong, Warit, Nonesung, Surapon, Jaknamon, Teetouch, Pengpun, Parinthapat, Taveekitworachai, Pittawat, Na-Thalang, Adisai, Sripaisarnmongkol, Sittipong, Jirayoot, Krisanapong, Tharnpipitchai, KasimaResearch paper

Resource information

Authors
Pipatanakul, Kunat, Manakul, Potsawee, Nitarach, Natapong, Sirichotedumrong, Warit, Nonesung, Surapon, Jaknamon, Teetouch, Pengpun, Parinthapat, Taveekitworachai, Pittawat, Na-Thalang, Adisai, Sripaisarnmongkol, Sittipong, Jirayoot, Krisanapong, Tharnpipitchai, Kasima
Research area
Artificial intelligence
Research topics
Computation and Language (cs.CL), Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences
Publication date
2024
DOI
10.48550/arxiv.2412.13702
Upstream last modified
Dec 19, 2024
License
Creative Commons Attribution 4.0 International
Last record update
Nov 5, 2026

About this resource

This paper introduces Typhoon 2, a series of text and multimodal large language models optimized for the Thai language. The series includes models for text, vision, and audio. Typhoon2-Text builds on state-of-the-art open models, such as Llama 3 and Qwen2, and we perform continual pre-training on a mixture of English and Thai data. We employ post-training techniques to enhance Thai language performance while preserving the base models' original capabilities. We release text models across a range of sizes, from 1 to 70 billion parameters, available in both base and instruction-tuned variants. To guardrail text generation, we release Typhoon2-Safety, a classifier enhanced for Thai cultures and language. Typhoon2-Vision improves Thai document understanding while retaining general visual capabilities, such as image captioning. Typhoon2-Audio introduces an end-to-end speech-to-speech model architecture capable of processing audio, speech, and text inputs and generating both text and speech outputs.