zelk12/MT1-Gen5-IMU-gemma-2-9B
Partial fine-tune vs zelk12/MT1-Gen5-IF-gemma-2-S2DMv1-9B. Partial change: 82% of the weights changed (attention, mlp, norms), in 42 of 42 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 34/169, MLP 126/126, Attention 168/168
1 derivatives checked
- mradermacher/MT1-Gen5-IMU-gemma-2-9B-GGUF: Same weights, converted