Getting openai.BadRequestError: Error code: 400: ‘Extra inputs are not permitted’ with an LLM model hosted on an on-prem GPU
I am not really able to find that much on this.
Here’s some discussion on Github. I was following this tutorial. Is the issue that I can’t use Mixtral with tool calling? Has anyone used Mixtral/some other local LLM models for Tool Calling? I am trying to figure out how to get this to work.