zelk12/MT2-Gen4-MM-gemma-2-Rv0.4MTM-9B

Full fine-tune vs recoilme/recoilme-gemma-2-9B-v0.4. Fine-tune: 91% of the weights changed, across 42 of 42 layers.

Tensors changed: lm_head 0/1, Embeddings 1/1, Norms 153/169, MLP 126/126, Attention 168/168

1 derivatives checked