jukofyork/Dusk-Miqu-70B

Partial fine-tune vs 152334H/miqu-1-70b-sf. Partial change: 68% of the weights changed (attention, lm_head, mlp, norms), in 72 of 80 layers.

Tensors changed: Embeddings 0/1, Norms 96/161, MLP 168/240, Attention 216/320, lm_head 1/1

2 derivatives checked