Lambent/Mira-v1.27-27B-dpo

Full fine-tune vs Lambent/Mira-v1.27-27B. Fine-tune: 99% of the weights changed, across 62 of 62 layers.

Tensors changed: Embeddings 1/4, Norms 92/484, MLP 205/294, Attention 274/464, other 1/1

2 derivatives checked

On the Hub · Downloads on Model Pulse