hus960/dolphin-2.8-mistral-7b-v02-Q4_K_M-GGUF
Full fine-tune vs mistral-community/Mistral-7B-v0.2. hus960/dolphin-2.8-mistral-7b-v02-Q4_K_M-GGUF is a GGUF (Q4_K_M) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 14/65, MLP 96/96, Attention 128/128