Need Help on New Model Deployed in HuggingFace

Deploy our own fine tuned model in hugging face .taken the Phi-3-mini-4k-instruct as base model.
While testing from local after downloaded files and passing the prompt along with 1 chunk and question .
We are not getting the response even though it is 2 hours.

1 Like

Could it be running on the CPU?
If so, no error will be displayed, but you may have to wait for several hours.