Closed Shivak11 closed 8 months ago
I just tried the huggingface script and it seems or be working for me. We are the AsyncInferenceClient
from the huggingface_hub
library. According to the comments in the code:
The model to run inference with. Can be a model id hosted on the Hugging Face Hub, e.g.
bigcode/starcoder
or a URL to a deployed Inference Endpoint. Defaults to None, in which case a recommended model is automatically selected for the task.
I tried the huggingface bot script. I am encountering a 404 error. Looks likes MODAL is expecting the model to be run locally. Is that correct?