huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated is a 14.8 billion parameter instruction-tuned language model derived from Qwen/Qwen2.5-14B-Instruct-1M. This model has been modified using an abliteration technique to remove refusal behaviors, offering an uncensored response capability. It maintains the original 131072 token context length and is primarily designed for applications requiring direct, unfiltered language generation.
No reviews yet. Be the first to review!
Hugging Face