grimjim/Magnolia-v1-Gemma2-8k-9B
Full fine-tune vs Delta-Vector/Odin-9B. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 1/1, Norms 134/169, MLP 126/126, Attention 168/168
3 derivatives checked
- mradermacher/Magnolia-v1-Gemma2-8k-9B-i1-GGUF: Quantization
- mradermacher/Magnolia-v1-Gemma2-8k-9B-GGUF: Same weights, converted
- grimjim/Magnolia-v2-Gemma2-8k-9B: Full fine-tune