grimjim/Kitsunebi-v1-Gemma2-8k-9B
Full fine-tune vs AXCXEPT/EZO-Common-9B-gemma-2-it. Fine-tune: 98% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 1/1, Norms 103/169, MLP 123/126, Attention 164/168
3 derivatives checked
- mradermacher/Kitsunebi-v1-Gemma2-8k-9B-i1-GGUF: Quantization
- mradermacher/Kitsunebi-v1-Gemma2-8k-9B-GGUF: Same weights, converted
- grimjim/Kitsunebi-v1-Gemma2-8k-9B-GGUF: Quantization