teddylee777/EEVE-Korean-Instruct-10.8B-v1.0-gguf
Full fine-tune vs yanolja/YanoljaNEXT-EEVE-10.8B. teddylee777/EEVE-Korean-Instruct-10.8B-v1.0-gguf is a GGUF (FP16) of different weights. Fine-tune: 98% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 144/144, Attention 192/192, lm_head 1/1