News for hackers. Stuff that matters.
Re:TinyGPT-V: Efficient Multimodal Large Language Model via ... by jn2clark on Thursday January 04, 2024 @12:30AM (#38863418)
Can anyone comment on an open source multi-modal LLM that can produce structured outputs based on an image? I have not found a good open source one yet (this included), seems to be only closed source that can do this reliably well. Any suggestions are very welcome!
Re:TinyGPT-V: Efficient Multimodal Large Language Model via ... by addandsubtract on Thursday January 04, 2024 @05:24AM (#38865357)
I've only used LLaVA / BakLLaVA. It falls under the LLAMA 2 Community License. Not sure if you consider that open source or not.
Re:TinyGPT-V: Efficient Multimodal Large Language Model via ... by isaacfung on Thursday January 04, 2024 @07:48AM (#38866344)
Something like this?

https://imgur.com/a/hPAaZUv

https://huggingface.co/spaces/Qwen/Qwen-VL-Plus

You can also ask it to give you bounding boxes of objects.