{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/typhoon-2-a-family-of-open-text-and","title":"Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models","arxiv_id":"2412.13702","date":"2024-12-18","proceeding":null,"authors":["Kunat Pipatanakul","Potsawee Manakul","Natapong Nitarach","Warit Sirichotedumrong","Surapon Nonesung","Teetouch Jaknamon","Parinthapat Pengpun","Pittawat Taveekitworachai","Adisai Na-Thalang","Sittipong Sripaisarnmongkol","Krisanapong Jirayoot","Kasima Tharnpipitchai"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2412.13702v2","url_pdf":"https://arxiv.org/pdf/2412.13702v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"typhoon-2-a-family-of-open-text-and","repo_url":"https://github.com/scb-10x/typhoon2-audio","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"document-understanding","task_name":"document understanding"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.13702","atlas_url":"https://app.syntology.ai/?focus=2412.13702","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}