rasyosef/gemma-4-E2B-it-dspark

Full fine-tune vs google/gemma-4-E2B-it. Fine-tune: 100% of the weights changed, across 5 of 5 layers.

Tensors changed: Norms 11/11, MLP 15/15, Attention 8/8

1 derivatives checked

• rasyosef/gemma-4-E2B-it-dspark-GGUF: Partial fine-tune

On the Hub · Downloads on Model Pulse