Securelayer7/salamandra-7b-instruct-Uncensored-Abliterated
Abliterated vs BSC-LT/salamandra-7b-instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 28 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 18/96, Attention 28/128, lm_head 0/1
2 derivatives checked
- mradermacher/salamandra-7b-instruct-Uncensored-Abliterated-i1-GGUF: Quantization
- mradermacher/salamandra-7b-instruct-Uncensored-Abliterated-GGUF: Same weights, converted