Uncensor any LLM with abliteration(huggingface.co)

450 points by mizzao 2 years ago | 228 comments

Hugging Face community blog post by Maxime Labonne explaining abliteration, a technique to remove refusal behavior from LLMs without retraining.

More than 80 AI models from Qualcomm(huggingface.co)

86 points by Brajeshwar 2 years ago | 35 comments

Qwen3-4B-Thinking-2507(huggingface.co)

151 points by IdealeZahlen 1 year ago | 51 comments

Qwen3-235B-A22B-Thinking-2507(huggingface.co)

129 points by tosh 1 year ago | 39 comments

Apertus 70B: Truly Open - Swiss LLM by ETH, EPFL and CSCS(huggingface.co)

280 points by denysvitali 1 year ago | 51 comments

Qwen3 30B-A3B(huggingface.co)

43 points by tosh 1 year ago | 9 comments