SC117/LFM2.5-VL-3B-Uncensored-GGUF

Abliterated (fewer layers) vs LiquidAI/LFM2.5-VL-3B. SC117/LFM2.5-VL-3B-Uncensored-GGUF matches part of LiquidAI/LFM2.5-VL-3B (244 of its 707 tensors; the rest of LiquidAI/LFM2.5-VL-3B has no counterpart). On the shared part: SC117/LFM2.5-VL-3B-Uncensored-GGUF is a GGUF (BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (out_proj, w2) changed, in 14 of 30 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.

Tensors changed: Embeddings 0/2, other 4/44, MLP 11/90, Norms 0/76, Attention 6/32

On the Hub · Downloads on Model Pulse