EveryonesGPT Vision Instruct. Single-turn English Only demo (CLIP ViT-L/14)

You must include an image. English Only.

https://raw.githubusercontent.com/HayatoHongo/EveryonesLLM/main/assets/ootemachi.jpg

Github Repo: https://github.com/HayatoHongo/EveryonesLLM.git

⚠️ The first message takes around 1 minute.

MultimodalTextbox