saidutta69/Qwen2.5-7B-Instruct-1M-heretic
Abliterated vs Qwen/Qwen2.5-7B-Instruct-1M. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 22 of 28 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 22/84, Attention 21/196, lm_head 0/1
2 derivatives checked
- mradermacher/Qwen2.5-7B-Instruct-1M-heretic-GGUF: Same weights, converted
- mradermacher/Qwen2.5-7B-Instruct-1M-heretic-i1-GGUF: Quantization