leochen085/SLIP
Partial fine-tune vs google/gemma-3-270m. Partial change: 9% of the weights changed (attention, mlp, norms), in 4 of 12 layers.
Tensors changed: Embeddings 0/1, Norms 18/73, MLP 12/36, Attention 16/48
Partial fine-tune vs google/gemma-3-270m. Partial change: 9% of the weights changed (attention, mlp, norms), in 4 of 12 layers.
Tensors changed: Embeddings 0/1, Norms 18/73, MLP 12/36, Attention 16/48