PRO Plan and for running huge models on free inference api?

Beginners
1

Hi,

I was curious about whether the pro plan would enable me to do the following:

curl /static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2FHuggingFaceH4%2Fstarchat-alpha%3C%2Fa%3E
-X POST
-d ‘{“inputs”: "Can you please let us know more details about your "}’
-H “Authorization: Bearer xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx”

As I am currently getting

{“error”:"The model HuggingFaceH4/starchat-alpha is too large to be loaded automatically (31GB > 10GB)…}

Best,
Jean Elbers

2

hi @jelber2,

This is a really large model, you may need a dedicated hardware , I recommend you looking at our Inference Endpoints - Hugging Face service and reaching out if you need help, thanks