News for hackers. Stuff that matters.

A comment on Omnivision-968M: Vision Language Model with 9x Tokens Reduction for Edge Devices. Parent comment

Re:Omnivision-968M: Vision Language Model with 9x Tokens Red... by alanzhuly on Thursday November 21, 2024 @05:20PM (#42209288)
Hi! I am from Nexa AI. We just improved Omnivision-968M based on your feedback! Here is a preview in our Hugging Face Space: https://huggingface.co/spaces/NexaAIDev/omnivlm-dpo-demo

The updated GGUF and safetensors will be released after final alignment tweaks. Please feel free to let us know if there's any other feedback!

[ Parent | on HN ]
Re:Omnivision-968M: Vision Language Model with 9x Tokens Red... by gizajob on Sunday November 24, 2024 @05:44AM (#42227180)
Why don’t you just hand-write the descriptions and then your AI won’t have to.
[ Parent | on HN ]