use the model offline

[ftufkc]

Can I deploy the model locally in a non-Internet environment and use StarCoder via the VS Code plugin? If so, how should I do it?

[yishanhong]

https://marketplace.visualstudio.com/items?itemName=HuggingFace.huggingface-vscode you can configure to make inference requests to your custom endpoint

[LucienShui]

https://github.com/huggingface/huggingface-vscode#configuring

Sure, you can deploy it locally then using endpoint to specific your own service.

[mat-l]

Which hardware specs does one need to run an endpoint locally? And do you have some performance metrics if one runs the inference on cpu or gpu?

[PrestigeDevop]

it would be cool if someone export onnx file and made public with restful endpoints on some - community donation type service