bunnycore/Sky-Maestro-7B-Sce
Full fine-tune vs NovaSky-AI/Sky-T1-mini. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 48/57, MLP 84/84, Attention 196/196
2 derivatives checked
- mradermacher/Sky-Maestro-7B-Sce-i1-GGUF: Quantization
- mradermacher/Sky-Maestro-7B-Sce-GGUF: Same weights, converted