正在加载视频...
视频加载失败
Last week we released Meta Chameleon: a new mixed-modal research model from Meta FAIR. Get the models ➡️ The 7B & 34B safety tuned models we’ve released can take any combination of text and images as input and produce text outputs using a new early fusion approach. While some... show more
10 条评论

Scott Hendricks2 年前
"safety tuned" lol

Abhishek Singh2 年前
Why not image output?

KellyV2 年前
Absolutely fantastic, but need a complete chameleon, not a castrated version.

Hunned Catz, Ph. D.2 年前
Why is image output not released?

Druvith2 年前
Why just text gen?

Carlos Alarcón2 年前
I hace an Issue with the download weights link :( HTTP request sent, awaiting response... 403 Forbidden 2024-06-25 17:20:39 ERROR 403: Forbidden.

Lynx2 年前
sounds good in theory but the modularity is gone

EyeSeeThru 👁️2 年前
👀

Kenny Le2 年前
That's fantastic news! Can't wait to see the new possibilities this brings to the AI community! Thank you Meta FAIR!

Sean2 年前
And what’s the news? we already knew this



