AALF/gemma-2-27b-it-SimPO-37K-100steps
Full fine-tune vs google/gemma-2-27b-it. Fine-tune: 100% of the weights changed, across 46 of 46 layers.
Tensors changed: Embeddings 1/1, Norms 69/185, MLP 138/138, Attention 184/184
5 derivatives checked
- bartowski/gemma-2-27b-it-SimPO-37K-100steps-GGUF: Same weights, converted
- mradermacher/gemma-2-27b-it-SimPO-37K-100steps-i1-GGUF: Quantization
- mradermacher/gemma-2-27b-it-SimPO-37K-100steps-GGUF: Quantization
- tensorblock/gemma-2-27b-it-SimPO-37K-100steps-GGUF: Quantization
- djuna/G2-BigGSHT-27B-2: Full fine-tune