tssst/nemo-gutenberg-12b-v2

Model Card for Model ID

A DPO qLORA finetune of Mistral Nemo 12b on four Gutenberg datasets plus one more dataset, approx ~9k lines.

Model Details

Model Description

Finetuned for 1 epoch on an A100 through Vast.AI.

Credits

Thank you to Axolotl for making finetuning easier. Thank you to Docker for... existing, I guess.

Changes from v1

• Base model changed to intervitens/mini-magnum-12b-v1.1
• Added nbeerbower/human-writing, which was supposed to be in v1 but I forgot to add it.
• Adjusted learning rate/other settings to compensate.

Addendum

You know, I am REALLY regretting panic-naming this line of models so ambiguously now. Well, too late now!