Last week we released Meta Chameleon: a new mixed-modal research model from Meta FAIR. Get the models ➡️ https://go.fb.me/hrkkgf Research paper ➡️ https://go.fb.me/u75dq8 The new safety tuned 7B and 34B models we’ve released for research use can take combinations of text and images as input and produce text outputs. Chameleon is one of the first publicly released approaches using a single unified architecture for both encoding and decoding using an early fusion approach. We’ve shared details on the full modeling approach and training in the new research paper, and we hope that the work we’re releasing will help to further democratize access to foundational mixed-modal models and empower others to streamline and scale their work in this space.
Looking forward to seeing how these advancements will shape future research and applications.
Great work!
Fantastic work! Meta Chameleon is a significant step forward in mixed-modal research. Excited to see how this unified architecture will empower more innovative applications and streamline workflows. Kudos to the team! 🚀
I read about it when the paper was released, just can’t wait !!
What’s the recommended GPU specs to run this
Why is it research only?
Will it be available at ollama.com ?
Impressive work from the researchers at Meta FAIR.
Weights when
Game changer for public use, first ever single unified architecture model available to public, go have fun with it if you are AI Enthusiast, just like us at Plima AI