Загрузка видео...
Не удалось загрузить видео
open d1 decision models are here! • small enough to run them on my macbook • multimodal for fun things like video input here i'm using d1-3B to rate how cute my outfit is. don't follow me for more fashion advice 💜 see more fun demos on our hugging... show more
11,098 просмотров • 4 дней назад •via X (Twitter)
Комментарии: 14

@ramin_m_h love it! will evaluate it on EdgeEvals clinical decision tasks 🔥 thanks for releasing it 🙌🏼

@ramin_m_h let us know what you think!

@ramin_m_h absolutely🤗

Reinforcement Learning from Human Fashion 💃

great demo idea!

thanks Morgan!

@ramin_m_h “D1” is for DIVINE 1 💅

🔥 Awesome use case

thank you!

Well, this is exactly one of the use-cases, I have to use decision models for, instead of fake or false matching scores or outfit ratings.

I am curious. How does it make a decision, on what base it knows that your outfit is cute?

We actually went deeper on how these decision models are changing the game for multimodal tasks here:

@liquidai Are there any resources on fine tuning d1 for a particular domain? Thank you!

12% is harsh lmao d1 not holding back


