Justine Tunney

If you're using the Python client library that's published by OpenAI, then it's not going to support features OpenAI doesn't have. However the llamafile server does support grammar. For example,...

No, I meant OpenAI. As far as I know, OpenAI hasn't devoted any engineering resources to adding support, in their Python client library, for features that are specific to llamafile...

You need to open the command prompt program and run your llamafile there, rather than double clicking on it.

Try downloading the llamafile executable from our github releases page and running `llamafile.exe -m llava-v1.5-7b-q4.llamafile`

This issue tracker is for bugs and feature requests. This isn't for support requests and even though we do our best to support you anyway, it's not acceptable to report...

Are you using ConEmu? https://github.com/Mozilla-Ocho/llamafile/issues/57#issuecomment-1846694678 What llamafile version are you using?

I can't reproduce this. Could you trying passing https://huggingface.co/Mozilla/Meta-Llama-3.1-8B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-8B-Instruct.Q5_K_M.llamafile as the `--model` flag? It may be an issue with your GGUF file metadata.

Hooray!

Are you familiar with our `.args` file hack? You can embed a file named `.args` in your llamafile as a zip asset and it'll use those as default arguments. It's...

As best as I can tell, what you're asking for is a somewhat different vision for the project, which we're happy to consider. For example, to accept a URL argument...