image/png

Mistral-Nemo-Gutenberg-Vitus-12B

Mistral-Nemo-Gutenberg-Encore-12B finetuned on nbeerbower/human-writing-dpo with Mistral Instruct.

Method

ORPO tuned with 1x RTX A6000 for 3 epochs.

Downloads last month
12
Safetensors
Model size
12.2B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for nbeerbower/Mistral-Nemo-Gutenberg-Vitus-12B

Dataset used to train nbeerbower/Mistral-Nemo-Gutenberg-Vitus-12B