mradermacher/Nemo-12b-Humanize-KTO-Experimental-2-GGUF
Full fine-tune vs cgato/Nemo-12b-Humanize-KTO-Experimental-2. mradermacher/Nemo-12b-Humanize-KTO-Experimental-2-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 44/81, MLP 120/120, Attention 160/160