Vision-CAIR/BFPO-Mistral-7b-v0.1
Abliterated vs mistralai/Mistral-7B-v0.1. Looks like abliteration (refusal removal): only the output projections (down_proj) changed, in 32 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 32/96, Attention 0/128, lm_head 0/1
2 derivatives checked
- mradermacher/BFPO-Mistral-7b-v0.1-i1-GGUF: Quantization
- mradermacher/BFPO-Mistral-7b-v0.1-GGUF: Same weights, converted