Open-Orca/Mixtral-SlimOrca-8x7B

Full fine-tune vs mistralai/Mixtral-8x7B-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 768/768, other 32/32, Norms 0/65, Attention 128/128

2 derivatives checked