Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
vikhyatk 
posted an update May 13
Post
1751
Cool new dataset from @isidentical - isidentical/moondream2-coyo-5M-captions

The VeCLIP paper showed a +3% gain while only using 14% of the data by synthetically captioning like this. You get diversity from the alt text (middle column) without having to deal with all of the noise.

I am new to AI arena and i am so glad that i landed on your space, Can you be my mentor. I am quick learner.
I have 18+ years of experience and was a developer few years back, and now want to code again and relearn ,

In this post