llmfan46/Ornith-1.0-35B-uncensored-heretic
Abliterated vs ornith-ai/Ornith-1.0-35B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 36 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/241, Attention 35/388, MLP 661/2366
6 derivatives checked
- mradermacher/Ornith-1.0-35B-uncensored-heretic-i1-GGUF: Quantization
- llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF: Same weights, converted
- mradermacher/Ornith-1.0-35B-uncensored-heretic-GGUF: Quantization
- leonsarmiento/Ornith-1.0-35B-uncensored-heretic-5bit-XL-mlx: Quantization
- noctrex/Ornith-1.0-35B-uncensored-heretic-MXFP4_MOE-GGUF: Quantization
- funnygeeker/Ornith-1.0-35B-uncensored-heretic-MLX-4bit: Quantization
3 other repos hold byte-for-byte identical weight files.