DazzlingXeno/Mystery-mag-try2

Full fine-tune vs 01-ai/Yi-1.5-34B-32K. Fine-tune: 100% of the weights changed, across 60 of 60 layers.

Tensors changed: Embeddings 1/1, Norms 44/121, MLP 180/180, Attention 240/240, lm_head 1/1

1 derivatives checked

On the Hub · Downloads on Model Pulse