Loading a model in an app when using HF Spaces

Hi,

I really love the concept of Huggingface Spaces. It works great for simple apps. But apps loading models from Huggingface does not work, I get the following:

OSError: We couldn't connect to 'https://huggingface.co' to load this file, couldn't find it in the cached files and it looks like Intel/neural-chat-7b-v3-1 is not the path to a directory containing a file named config.json. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/transformers/installation#offline-mode'.

Does this mean that the docker-based Space cannot access internet models and that I need to download model files locally? Thanks!

1 Like