jorkle/Muse-Glimmer-30B-Abliterated-Aggressive
Abliterated vs meta-models/Muse-Glimmer-30B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 52 of 52 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/3, Norms 0/413, MLP 52/358, Attention 52/660, lm_head 0/1, other 0/1
2 derivatives checked
- mradermacher/Muse-Glimmer-30B-Abliterated-Aggressive-i1-GGUF: Quantization
- mradermacher/Muse-Glimmer-30B-Abliterated-Aggressive-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.