v000000/L3.1-Niitorm-8B-t0.0001

Partial fine-tune vs Sao10K/L3.1-8B-Niitama-v1.1. Partial change: 85% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 6/65, MLP 94/96, Attention 126/128

2 derivatives checked