Tsunami-th/Tsunami-0.5x-7B-Instruct
Tsunami-th/Tsunami-0.5x-7B-Instruct is a 7.6 billion parameter Thai Large Language Model fine-tuned from Qwen2.5-7B by Pollakrit Lorprasertkul. It was trained on approximately 100,000 rows of Thai dataset, making it specialized for Thai language understanding and generation. This model is an initial version, with a full 1.0 release planned, and utilizes the ChatML prompt template.
Loading preview...
Tsunami-0.5x-7B-Instruct Overview
Tsunami-0.5x-7B-Instruct is a 7.6 billion parameter Thai Large Language Model developed by Pollakrit Lorprasertkul. It is fine-tuned from the Qwen2.5-7B base model, specifically optimized for the Thai language. This version represents an initial release, having been trained on approximately 100,000 rows of Thai-specific data.
Key Capabilities
- Thai Language Proficiency: Specialized in understanding and generating text in Thai due to its targeted fine-tuning dataset.
- Qwen2.5-7B Foundation: Leverages the robust architecture and capabilities of the Qwen2.5-7B model.
- ChatML Prompt Template: Designed to work with the ChatML format for conversational AI applications.
Performance Insights
Evaluations on the Open LLM Leaderboard show an average score of 29.80. Specific metrics include:
- IFEval (0-Shot): 70.99
- BBH (3-Shot): 37.36
- MMLU-PRO (5-shot): 38.42
Good for
- Applications requiring strong performance in the Thai language.
- Developers looking for a Qwen2.5-7B based model with Thai language specialization.
- Experimentation with instruction-tuned models for Thai-centric tasks.