mlasli/Muse-Glimmer-30B-Abliterated-BF16
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
4 derivatives checked
- mlasli/Muse-Glimmer-30B-Abliterated-Q4_K_M-GGUF: Quantization
- mlasli/Muse-Glimmer-30B-Abliterated-Q6_K-GGUF: Quantization
- mlasli/Muse-Glimmer-30B-Abliterated-FP16-GGUF: Same weights, converted
- mlasli/Muse-Glimmer-30B-Abliterated-Q8_0-GGUF: Quantization