google/datagemma-rag-27b-it
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 112/185, MLP 138/138, Attention 184/184
8 derivatives checked
- bartowski/datagemma-rag-27b-it-GGUF: Same weights, converted
- legraphista/datagemma-rag-27b-it-IMat-GGUF: Same weights, converted
- mradermacher/datagemma-rag-27b-it-i1-GGUF: Quantization
- second-state/datagemma-rag-27b-it-GGUF: Same weights, converted
- mradermacher/datagemma-rag-27b-it-GGUF: Quantization
- gaianet/datagemma-rag-27b-it-GGUF: Same weights, converted
- lmstudio-community/datagemma-rag-27b-it-GGUF: Quantization
- DevQuasar-3/datagemma-rag-27b-it-GGUF: Quantization