chuanli11/Llama-3.2-3B-Instruct-uncensored

chuanli11/Llama-3.2-3B-Instruct-uncensored is a 3.2 billion parameter instruction-tuned causal language model based on the Llama-3.2 architecture. Developed by chuanli11, this model is an uncensored variant of the original Llama-3.2-3B-Instruct, specifically modified to reduce refusal to respond to sensitive queries. It is primarily designed for research into model safety and behavior, offering responses to topics that the censored base model would typically decline.