katsukiono/EqualFrontiers-iko-v2

Partial fine-tune vs google/gemma-3-1b-it. Partial change: 70% of the weights changed (attention, mlp, norms), in 26 of 26 layers.

Tensors changed: Embeddings 0/1, Norms 68/157, MLP 78/78, Attention 104/104

1 derivatives checked

• katsukiono/EqualFrontiers-iko-v2-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse