zelk12/MT3-Gen5-MAI-gemma-2-9B_v1
Full fine-tune vs zelk12/MT3-Gen5-IF-gemma-2-Av4dMT2-9B_v1. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 169/169, MLP 126/126, Attention 168/168
2 derivatives checked
- mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF: Same weights, converted
- zelk12/MT3-Gen5-gemma-2-9B_v1: Full fine-tune