Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
alvarobartt 
posted an update Dec 27, 2023
alvarobartt

Also thanks to @osanseviero for granting me access for the posts private beta! 🦙

osanseviero

Very cool! So this is DPO^2 🔥

·
alvarobartt

Yes, indeed for anyone wondering, a bit more into detail, Mixtral-8x7B-Instruct-v0.1 was fine-tuned using SFT + DPO (read more about it at https://mistral.ai/news/mixtral-of-experts/) and we ran the DPO fine-tuning on top of it, but using data from UltraFeedback, in particular argilla/ultrafeedback-binarized-preferences-cleaned, but using a different binarization approach and applying some data cleaning, but essentially following the same approach as @HuggingFaceH4 did with zephyr-7b-beta.

So DPO ^ 2 is fair! 😄

Roblox22r

spaces demo?

·
alvarobartt

We may need to discuss that internally, but could be something we may consider for opening 2024 🤗

iarbel

Very cool, thanks for sharing.

How does it perform on MT-Bench / Alpaca-eval?

·
alvarobartt

MT-Bench is on par with mistralai/Mixtral-8x7B-Instruct-v0.1 which means ~8.3, and we didn't run AlpacaEval yet

blevlabs

This is great! Unfortunately it does not work on Inference Endpoints, will have to try and find some other way to host the model.

·
alvarobartt

Hey sorry to hear that, is it due to the resources required to run it right? Maybe you can ask HuggingFace for a quota increase so that you can allocate the required resources 🤗 Let me know if there's anything I can help you with!

cryptoakunn2
This comment has been hidden
In this post