QuantFactory/shisa-7b-v1-GGUF
Full fine-tune vs augmxnt/shisa-base-7b-v1. QuantFactory/shisa-7b-v1-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 16/65, MLP 96/96, Attention 128/128