andyoneal/Gemma-4-E4B-Nightcap
Partial fine-tune vs AuriAetherwiing/G4-E4B-Musica-v1. Partial change: 58% of the weights changed (attention, embeddings, mlp, norms, other), in 42 of 42 layers.
Tensors changed: MLP 126/606, Norms 112/502, other 85/261, Attention 132/755, Embeddings 1/6
1 derivatives checked
- andyoneal/Gemma-4-E4B-Nightcap-GGUF: Quantization (fewer layers)