Hugging Face's logo

Phind
/
Phind-CodeLlama-34B-v1

Text Generation
Transformers
PyTorch
llama
code llama
Eval Results
Inference Endpoints
text-generation-inference
Model card Files Community
10

VS Code integration

#3
by VadimP - opened
Discussion
VadimP

What are some ways one can use this model right inside vscode?

I just know of FauxPilot but that hasn't been updated recently.

n-vigano

Maybe you could ask for integration to the author of TurboPilot

cgaalev

you can use the Continue VSCode extension, installation detailled in : https://github.com/xNul/code-llama-for-vscode

rjmacarthy

I created a vscode extension for it easy to install and run locally if you have the compute.

https://github.com/rjmacarthy/twinny

DanRegalia

What is the memory requirement for this model? Will it run on a local P40 24gb?

Sign up or log in to comment