The most no-nonsense, locally or API-hosted AI code completion plugin for Visual Studio Code - like GitHub Copilot but completely free and 100% private.
When I was setting up twinny today I followed the instructions here but the requests to the server would end up in 404. This was because as per docs the codelama:7b model itself was pulled but not the instruct or code variants. The ollama OpenAI API will 404 and return {"error":"model 'XXX' not found, try pulling it first"}.
When I was setting up twinny today I followed the instructions here but the requests to the server would end up in 404. This was because as per docs the codelama:7b model itself was pulled but not the instruct or code variants. The ollama OpenAI API will 404 and return {"error":"model 'XXX' not found, try pulling it first"}.