scima/whittle-14.7b-scima
Full fine-tune vs logic65/Qwen3.8-Whittle-tri-14.7B. scima/whittle-14.7b-scima is a GGUF (FP16) of different weights. Fine-tune: 100% of the weights changed, across 0 of 0 layers.
Tensors changed: lm_head 1/1, Norms 0/105, other 91/145, Attention 80/80, MLP 96/96