qgallouedec/gemma-3-12b-it-codeforces-SFT
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 241/400, MLP 144/252, Attention 192/408, other 0/1
3 derivatives checked
- BasedAGI/Gemma-3-12B-IT-Codeforces-SFT-i1-GGUF: Quantization (fewer layers)
- mradermacher/gemma-3-12b-it-codeforces-SFT-i1-GGUF: Quantization (fewer layers)
- mradermacher/gemma-3-12b-it-codeforces-SFT-GGUF: Quantization (fewer layers)