rtzr/ko-gemma-2-9b-it
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
4 derivatives checked
- mradermacher/ko-gemma-2-9b-it-i1-GGUF: Quantization
- QuantFactory/ko-gemma-2-9b-it-GGUF: Quantization
- KIST-robot-intelligence/ko-gemma-2-9b-it-GGUF-quantization: Same weights, converted
- mradermacher/ko-gemma-2-9b-it-GGUF: Same weights, converted