MuXodious/LongWriter-llama3.1-8B-absolute-heresy
Abliterated vs zai-org/LongWriter-llama3.1-8b. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 24 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 24/96, Attention 21/128, lm_head 0/1
2 derivatives checked
- mradermacher/LongWriter-llama3.1-8B-absolute-heresy-i1-GGUF: Quantization
- mradermacher/LongWriter-llama3.1-8B-absolute-heresy-GGUF: Same weights, converted