feat: use codellama:code for code completions
What does this merge request do and why?
Code-Llama has a dedicated model for completions, thus register its code
variant to be used for code completions.
In order to allow codellama to be used for both generations and completions, the litellm config would look like this:
model_list:
- model_name: codellama
litellm_params:
model: ollama/codellama:13b
api_base: http://localhost:11434
- model_name: codellama:code
litellm_params:
model: ollama/codellama:13b-code
api_base: http://localhost:11434
How to set up and validate locally
Numbered steps to set up and validate the change are strongly suggested.
Merge request checklist
-
Tests added for new functionality. If not, please raise an issue to follow up. -
Documentation added/updated, if needed.
Edited by Bruno Cardoso