AELLM/gemma-2-inko-9b
Full fine-tune vs BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 1/1, Norms 85/169, MLP 126/126, Attention 168/168
1 derivatives checked
- mradermacher/gemma-2-inko-9b-GGUF: Same weights, converted