fix: use /infill for llama.cpp code-completions

carlrobertoh / CodeGPT

JetBrains extension providing access to state-of-the-art LLMs, such as GPT-4, Claude 3, Code Llama, and others, all for free

https://codegpt.ee

Apache License 2.0

912 stars 186 forks source link

Closed PhilKes closed 2 months ago

PhilKes commented 2 months ago

Use /infill for Llama.CPP code-completions instead of /chat/completions as suggested in https://github.com/carlrobertoh/CodeGPT/pull/510#issuecomment-2077027810