mergekit-community/Usp
Full fine-tune vs TheDrummer/UnslopNemo-12B-v4.1. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 79/81, MLP 120/120, Attention 160/160
1 derivatives checked
- mradermacher/Usp-GGUF: Quantization