DazzlingXeno/Mystery-Magnum

Partial fine-tune vs 01-ai/Yi-1.5-34B-32K. Partial change: 51% of the weights changed (attention, embeddings, lm_head, mlp), in 60 of 60 layers.

Tensors changed: Embeddings 1/1, Norms 0/121, MLP 90/180, Attention 120/240, lm_head 1/1

2 derivatives checked