aisingapore/Gemma-SEA-Guard-12B-2602

Full fine-tune vs google/gemma-3-12b-it. Fine-tune: 97% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 1/4, Norms 201/400, MLP 144/252, Attention 192/408, other 0/1

2 derivatives checked

• mradermacher/Gemma-SEA-Guard-12B-2602-i1-GGUF: Quantization (fewer layers)
• mradermacher/Gemma-SEA-Guard-12B-2602-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse