News for hackers. Stuff that matters.

A comment on T0* – Series of encoder-decoder models trained on a large set of different tasks. Parent comment

Re:T0* – Series of encoder-decoder models trained on a large... by Lokinew on Monday October 18, 2021 @10:55AM (#28906049)
Just in case this question isn't to far out of your way. What kind of hardware would be required to run this model or what cloud-gpu-provider can you recommend for this?
[ Parent | on HN ]
Re:T0* – Series of encoder-decoder models trained on a large... by srush on Monday October 18, 2021 @11:32AM (#28906492)
from @craffel: It's possible to run inference on a single Google Cloud TPU v3-8 device or on a server with 4x 32GB v100 GPUs. Hugging Face also has an inference API for any model on the Hub: https://api-inference.huggingface.co/docs/python/html/index....
[ Parent | on HN ]