DoppelReflEx/MN-12B-Kakigori
Full fine-tune vs cgato/Nemo-12b-Humanize-KTO-Experimental-Latest. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 46/81, MLP 120/120, Attention 160/160
2 derivatives checked
- mradermacher/MN-12B-Kakigori-i1-GGUF: Quantization
- mradermacher/MN-12B-Kakigori-GGUF: Quantization