WithinUsAI/Gemma3-Prompt.Coder.it.Uncensored-270m

Full fine-tune vs AxionLab-official/DogeAI-v1.5-Coder. Fine-tune: 100% of the weights changed, across 18 of 18 layers.

Tensors changed: Embeddings 1/1, Norms 109/109, MLP 54/54, Attention 72/72

1 derivatives checked

• mradermacher/Gemma-3-Prompt-Coder-270m-it-Uncensored-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse