zelk12/MT1-Gen3-MMMA-gemma-2-9B

Full fine-tune vs zelk12/MT1-Gen3-MA-gemma-2-S5Av4d-9B. Fine-tune: 100% of the weights changed, across 42 of 42 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 166/169, MLP 126/126, Attention 168/168

2 derivatives checked

• mradermacher/MT1-Gen3-MMMA-gemma-2-9B-GGUF: Same weights, converted
• zelk12/MT1-Gen3-MMMAMUI-gemma-2-9B: Full fine-tune

On the Hub · Downloads on Model Pulse