augmxnt/Qwen2-7B-Instruct-deccp
Abliterated vs Qwen/Qwen2-7B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 27 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 27/84, Attention 27/196, lm_head 0/1
3 derivatives checked
- mradermacher/Qwen2-7B-Instruct-deccp-i1-GGUF: Quantization
- QuantFactory/Qwen2-7B-Instruct-deccp-GGUF: Quantization
- mradermacher/Qwen2-7B-Instruct-deccp-GGUF: Same weights, converted