yolay/RAIF-DeepScaleR-1.5B

Partial fine-tune vs agentica-org/DeepScaleR-1.5B-Preview. Partial change: 87% of the weights changed (attention, lm_head, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1

1 derivatives checked

On the Hub · Downloads on Model Pulse