rAIfle/Questionable-MN-bf16

Full fine-tune vs mistralai/Mistral-Nemo-Base-2407. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 0/81, MLP 120/120, Attention 160/160, lm_head 1/1

3 derivatives checked