google/shieldgemma-2-4b-it
Full fine-tune vs google/gemma-3-4b-pt. Fine-tune: 90% of the weights changed, across 34 of 34 layers.
Tensors changed: Embeddings 1/4, Norms 206/316, MLP 102/210, Attention 136/352, other 1/1
1 derivatives checked
- infil00p/shieldgemma-2-4b-it-GGUF: Full fine-tune
3 other repos hold byte-for-byte identical weight files.