ToastyPigeon/gemma-3-starshine-merge-B

Full fine-tune vs ToastyPigeon/Gemma-3-Starshine-12B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 4/4, Norms 399/400, MLP 252/252, Attention 408/408, other 1/1

2 derivatives checked

• mradermacher/gemma-3-starshine-merge-B-i1-GGUF: Quantization (fewer layers)
• mradermacher/gemma-3-starshine-merge-B-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse