qgallouedec/gemma-3-27b-it-codeforces-SFT

Full fine-tune vs google/gemma-3-27b-it. Fine-tune: 98% of the weights changed, across 62 of 62 layers.

Tensors changed: Embeddings 1/4, Norms 318/484, MLP 186/294, Attention 248/464, other 0/1

2 derivatives checked

• bartowski/qgallouedec_gemma-3-27b-it-codeforces-SFT-GGUF: Same weights, converted (fewer layers)
• BasedAGI/Gemma-3-27B-IT-Codeforces-SFT-i1-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse