cjvt/GaMS-9B
Full fine-tune vs google/gemma-2-9b. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 1/1, Norms 169/169, MLP 126/126, Attention 168/168
3 derivatives checked
- cjvt/GaMS-9B-Instruct: Full fine-tune
- mradermacher/GaMS-9B-i1-GGUF: Quantization
- mradermacher/GaMS-9B-GGUF: Same weights, converted