Blog Grid

Lorem ipsum dolor sit amet, consectetur adipiscing elit. In varius eros eget sapien consectetur ultrices. Ut quis dapibus libero.

Researchimage

Finetuning Mixtral 8x7B with SFT and DPO

We describe the finetuning experiments we have done to illustrate the effectiveness of SFT and DPO with the state-of-the-art Mixtral 8x7B model.

author

By Bryan Wen

AI Researcher

Date

2024-02-24