QuantFactory/medius-erebus-magnum-14b-GGUF
Full fine-tune vs Qwen/Qwen2.5-14B. QuantFactory/medius-erebus-magnum-14b-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 95/97, MLP 144/144, Attention 336/336