prithivMLmods/NeoHorse-1-4B-Max-Heretic-Uncensored-TURBO
Abliterated vs TokenRhythm/NeoHorse-1-4B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 27 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/105, Attention 27/224, MLP 18/96
2 derivatives checked
- mradermacher/NeoHorse-1-4B-Max-Heretic-Uncensored-TURBO-i1-GGUF: Quantization
- mradermacher/NeoHorse-1-4B-Max-Heretic-Uncensored-TURBO-GGUF: Same weights, converted