zaakirio/LFM2.5-8B-A1B-Uncensored
Abliterated vs LiquidAI/LFM2.5-8B-A1B. Looks like abliteration (refusal removal): only the output projections (out_proj) changed, in 14 of 24 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: MLP 0/2162, Embeddings 0/2, other 10/54, Norms 0/60, Attention 4/24
2 derivatives checked
- zaakirio/LFM2.5-8B-A1B-Uncensored-GGUF: Same weights, converted
- lopezjhonf/LFM2.5-8B-A1B-Uncensored-GGUF: Quantization