DireDreadlord/GemCod-codegen-270M

Full fine-tune vs google/gemma-3-270m-it. Fine-tune: 100% of the weights changed, across 18 of 18 layers.

Tensors changed: Norms 18/109, MLP 54/54, Attention 72/72

1 derivatives checked

• mradermacher/GemCod-codegen-270M-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse