BarBarickoza/Picaro-MagNante-v4-v1-12b
Full fine-tune vs TheDrummer/Rocinante-12B-v1. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 41/81, MLP 120/120, Attention 160/160
2 derivatives checked
- mradermacher/Picaro-MagNante-v4-v1-12b-i1-GGUF: Quantization
- mradermacher/Picaro-MagNante-v4-v1-12b-GGUF: Quantization