Dexmal/DM05-MEM-Robodojo-Sim

Partial fine-tune vs Dexmal/DM05. Partial change: 77% of the weights changed (attention, embeddings, mlp, norms, other), in 34 of 34 layers.

Tensors changed: other 75/75, Norms 451/521, MLP 384/384, Attention 488/488, lm_head 0/1, Embeddings 3/4

On the Hub · Downloads on Model Pulse