News for hackers. Stuff that matters.
Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ... by abrichr on Tuesday May 28, 2024 @10:25PM (#40507766)
It's very reliable for GUI segment understanding; see e.g. https://github.com/OpenAdaptAI/OpenAdapt/pull/610 (scroll down to `gpt-4-vision-preview`).
Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ... by amelius on Wednesday May 29, 2024 @07:55AM (#40510952)
Can it be used for automatic annotation?

As in: you tell it that these and these parts should be masked such and such, and then it does that?

Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ... by abrichr on Wednesday May 29, 2024 @09:53AM (#40512032)
We have not had success with that unfortunately.
Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ... by amelius on Wednesday May 29, 2024 @10:05AM (#40512157)
Thank you, your comment will save me some trouble ;)