Closed vitalyshalumov closed 6 months ago
The FAQ for launching llava and arguments for h2ogpt are the same.
https://github.com/h2oai/h2ogpt/blob/main/docs/FAQ.md#llava-vision-models
Docker arguments are nothing special, but one should ensure to pass through ports gradio llava uses, e.g. 7861 in the above FAQ example. Options like --llava_model
need to be passed along.
If these two things (port and llava_model) are not clear, let me know.
If I use TGI, how to specify the inputs?
Did you try the 2 things I mentioned? llava stuff is unrelated to TGI.
I'm trying to use TGI for llava inference, as I would for any other model. Besides the --llava_model option, how is this different from LLM usecases?
I don't think TGI, vLLM, etc. support llava. I know ollama does, which maybe better esp for smaller systems.
Please provide guidelines for enabling Vision Models window in the UI for image upload.