ElementMerc/llama-3.2-1b-abliterated
Abliterated vs meta-llama/Llama-3.2-1B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 7 of 16 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 7/48, Attention 7/64
3 derivatives checked
- mradermacher/llama-3.2-1b-abliterated-i1-GGUF: Quantization
- mradermacher/llama-3.2-1b-abliterated-GGUF: Same weights, converted
- ElementMerc/llama-3.2-1b-abliterated-GGUF: Same weights, converted