QuantFactory/EXAONE-Deep-7.8B-GGUF
Full fine-tune vs LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct. QuantFactory/EXAONE-Deep-7.8B-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Attention 128/128, Norms 50/65, MLP 96/96, Embeddings 1/1, lm_head 1/1