FuseChat-Qwen-2.5-7B-Instruct-Heretic is a 7 billion parameter instruction-tuned causal language model, a decensored version of FuseAI's Qwen-2.5-7B-Instruct. Developed by ChiKoi7 using the Heretic tool, this model significantly reduces refusal rates compared to its original counterpart. It is primarily optimized for general conversation, instruction following, mathematics, and coding tasks, leveraging an implicit model fusion training approach.
No reviews yet. Be the first to review!