Ray2333/GRM-Gemma2-2B-sftreg

Full fine-tune vs google/gemma-2-2b-it. Fine-tune: 100% of the weights changed, across 26 of 26 layers.

Tensors changed: Embeddings 1/1, Norms 90/105, MLP 78/78, Attention 104/104

1 derivatives checked

• Ray2333/GRM-gemma2-2B-rewardmodel-ft: Partial fine-tune

On the Hub · Downloads on Model Pulse