Infinity-Instruct-7M-Gen-Llama3_1-8B is an 8 billion parameter instruction-tuned language model developed by the Beijing Academy of Artificial Intelligence (BAAI). This model is fine-tuned on the Infinity-Instruct-7M and Infinity-Instruct-Gen datasets without reinforcement learning from human feedback (RLHF). It demonstrates strong performance on AlpacaEval 2.0, showing favorable results compared to GPT-4, and is designed for general instruction-following and chat applications.
No reviews yet. Be the first to review!