Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910753961803776 |
|---|---|
| author | 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 |
| author_facet | 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 |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_13702 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models 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 Computation and Language Artificial Intelligence 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. |
| title | Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2412.13702 |