zelk12/MT1-Gen5-BB-gemma-2-S4Av4d-9B

Partial fine-tune vs lemon07r/Gemma-2-Ataraxy-v4d-9B. Partial change: 78% of the weights changed (attention, mlp, norms), in 40 of 42 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 149/169, MLP 120/126, Attention 160/168

2 derivatives checked

• mradermacher/MT1-Gen5-BB-gemma-2-S4Av4d-9B-GGUF: Same weights, converted
• zelk12/MT1-Gen5-BMM-gemma-2-9B: Partial fine-tune

On the Hub · Downloads on Model Pulse