karakuri-ai/karakuri-lm-8x7b-instruct-v0.1

Full fine-tune vs tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

3 derivatives checked