litellm.drop_params error when running the openapi server

Nobody has claimed this yet.

I'm running the server normally with: python -m routellm.openai_server --routers mf --weak-model ollama_chat/codeqwen
and am getting this whenever I attempt a prompt:

File "C:\Users\nate\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\litellm\utils.py", line 3586, in get_optional_params
_check_valid_arg(supported_params=supported_params)
File "C:\Users\nate\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\litellm\utils.py", line 3060, in _check_valid_arg
raise UnsupportedParamsError(
litellm.exceptions.UnsupportedParamsError: litellm.UnsupportedParamsError: ollama_chat does not support parameters: {'presence_penalty': 0.0}, for model=codeqwen. To drop these, set `litellm.drop_params=True` or for proxy:

`litellm_settings:
drop_params: true`

I've tried modifying the yaml to no avail.
Please help!

Start by reproducing the failure with the documented `python -m routellm.openai_server` command and the `ollama_chat/codeqwen` model. Inspect how the OpenAPI server builds request parameters and how its YAML configuration is loaded; done means the request succeeds without the unsupported `presence_penalty` error and the intended `drop_params` setting is honored.

Written by the indexing model from the issue text.