saidutta69/DeepSeek-R1-Qwen3-8B-heretic

Abliterated vs deepseek-ai/DeepSeek-R1-0528-Qwen3-8B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 35 of 36 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.

Tensors changed: Embeddings 0/1, Attention 35/144, Norms 0/145, MLP 30/108, lm_head 0/1

On the Hub · Downloads on Model Pulse