zelk12/MT1-Gen5-MU-gemma-2-S2Qv1-9B

Full fine-tune vs sam-paech/Quill-v1. Fine-tune: 90% of the weights changed, across 42 of 42 layers.

Tensors changed: Embeddings 0/1, Norms 147/169, MLP 126/126, Attention 168/168

1 derivatives checked

• mradermacher/MT1-Gen5-MU-gemma-2-S2Qv1-9B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse