Heralax/Mannerstral-base
Full fine-tune vs mistral-community/Mistral-7B-v0.2. Heralax/Mannerstral-base is a GGUF (F16) 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