zhichen/Llama3-Chinese

Llama3-Chinese is an 8 billion parameter language model developed by Zhichen Zhang, Xin LU, and Long Chen, based on Meta-Llama-3-8B. It is fine-tuned using DORA and LORA+ methods on 500k high-quality Chinese multi-turn SFT data and 100k English multi-turn SFT data. This model is specifically optimized for enhanced performance in Chinese language understanding and generation tasks, making it suitable for applications requiring strong bilingual capabilities.