Using local models // Running locally

OpenCodeInterpreter / OpenCodeInterpreter

OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. It significantly enhances code generation capabilities by integrating execution and iterative refinement functionalities.

https://opencodeinterpreter.github.io/

Apache License 2.0

1.49k stars 198 forks source link

Using local models // Running locally #22

Open yuisheaven opened 2 months ago

yuisheaven commented 2 months ago

Hello,

currently I feel forced to use huggingface for inference which is not an option for what I am trying to do. Is it possible to use the OpenCodeInterpreter completely locally by also running the models locally? For example with Ollama or AnythingLLM?

shallker commented 2 months ago

Same question here, or does some service provider run this model on his server and provide an API access?