vandijklab/C2S-Scale-Gemma-2-27B
Full fine-tune vs google/gemma-2-27b. Fine-tune: 100% of the weights changed, across 46 of 46 layers.
Tensors changed: Embeddings 1/1, Attention 184/184, Norms 185/185, MLP 138/138
3 derivatives checked
- mradermacher/C2S-Scale-Gemma-2-27B-GGUF: Quantization
- DevQuasar/vandijklab.C2S-Scale-Gemma-2-27B-GGUF: Same weights, converted
- MarselM/C2S-Scale-Gemma-2-27B-GGUF: Quantization
3 other repos hold byte-for-byte identical weight files.