Dexmal/DM05-libero

Partial fine-tune vs Dexmal/DM05. Partial change: 75% of the weights changed (attention, embeddings, mlp, norms, other), in 34 of 34 layers.

Tensors changed: other 75/75, Norms 439/521, MLP 380/384, Attention 486/488, lm_head 0/1, Embeddings 3/4

On the Hub · Downloads on Model Pulse