SC117/Spark-X2.5-4B-abliterated-FIT-GGUF
Abliterated vs XHToken/Spark-X2.5-4B. SC117/Spark-X2.5-4B-abliterated-FIT-GGUF is a GGUF (BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, out_proj) changed, in 7 of 36 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 6/108, Attention 7/72
1 derivatives checked
- bumblebuttpow/Spark-X2.5-4B-abliterated-MLX-8bit: Quantization