Tsunami-th/Tsunami-0.5-7B-Instruct

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Oct 11, 2024License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Tsunami-th/Tsunami-0.5-7B-Instruct is a 7.6 billion parameter Thai Large Language Model developed by Pollakrit Lorprasertkul. Fine-tuned from Qwen2.5-7B on approximately 60,000 rows of Thai-specific domain data, this model specializes in understanding and generating Thai language. It is designed for applications requiring robust performance in Thai natural language processing tasks, leveraging its specialized training for enhanced relevance and accuracy in the Thai context.

Loading preview...

Tsunami-0.5-7B-Instruct Overview

Tsunami-0.5-7B-Instruct is a 7.6 billion parameter Thai Large Language Model, fine-tuned from the Qwen2.5-7B architecture. Developed by Pollakrit Lorprasertkul, this model is specifically designed to excel in Thai language processing tasks. It has undergone specialized training on approximately 60,000 rows of Thai-specific domain data, making it particularly adept at understanding and generating content relevant to the Thai context.

Key Capabilities

  • Thai Language Specialization: Optimized for performance in Thai natural language understanding and generation.
  • Instruction Following: Fine-tuned to follow instructions effectively, leveraging the ChatML prompt template.
  • Qwen2.5-7B Foundation: Built upon the robust Qwen2.5-7B model, inheriting its strong base capabilities.

Good For

  • Applications requiring high accuracy in Thai text generation and comprehension.
  • Developers building chatbots, content creation tools, or other NLP systems for the Thai market.
  • Research and development in Thai large language models, serving as a specialized base model.