Improved documentation on how to use local model

choderalab / espaloma

Extensible Surrogate Potential of Ab initio Learned and Optimized by Message-passing Algorithm 🍹https://arxiv.org/abs/2010.01196

https://docs.espaloma.org/en/latest/

MIT License

202 stars 23 forks source link

Improved documentation on how to use local model #182

Closed ijpulidos closed 10 months ago

ijpulidos commented 10 months ago

It was noted in https://github.com/choderalab/espaloma/issues/181 that loading a model that has been previously downloaded in .pt format needs a call to the eval method to have correct predictions/inference using the model.

mikemhenry commented 10 months ago

Yes I think it could use a mention since this is quite a foot gun, which is why in the quick start we list using the esp.get_model function.

We probably need to grep our examples and snippets and make sure we call eval() or use esp.get_model

ijpulidos commented 10 months ago

I believe only the main README.md and the deploy.rst files are the ones that should have changes here, as far as I can see. Added the changes for the README file to the PR.