lmg-anon/vntl-gemma2-2b-gguf
Full fine-tune vs rinna/gemma-2-baku-2b. lmg-anon/vntl-gemma2-2b-gguf is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Norms 103/105, MLP 78/78, Attention 104/104