zaakirio/LFM2.5-1.2B-Instruct-Uncensored
Abliterated vs LiquidAI/LFM2.5-1.2B-Instruct. Looks like abliteration (refusal removal): only the output projections (out_proj, w2) changed, in 12 of 16 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/2, other 7/30, MLP 10/48, Norms 0/44, Attention 5/24
3 derivatives checked
- zaakirio/LFM2.5-1.2B-Instruct-Uncensored-GGUF: Quantization
- mradermacher/LFM2.5-1.2B-Instruct-Uncensored-i1-GGUF: Quantization
- mradermacher/LFM2.5-1.2B-Instruct-Uncensored-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.