Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
bloom
Eval Results
text-generation-inference
Inference Endpoints

Bloom Inference API has been reporting as overloaded all day (1/29/23)

#179
by bicx - opened

I have been receiving the error "Model is overloaded, please wait for a bit" every time I've tried using the bloom Inference API in the last 16 hours. I'm a new user (Pro plan, if that makes any difference) trying to get started, and I haven't yet made a successful API call. Is there anything that commonly triggers this error, or is this a true overload?

BigScience Workshop org

I just tried it and it seems fine

Sign up or log in to comment