Anyone know where to get access to a server with GPUs that might be better than AWS?
Currently running a model from HuggingFace hub as part of the pipeline, and it's fairly slow on the G4 instances they have available
a
Aqeel Ali
04/16/2023, 4:32 PM
Nader, from brev.dev is a participant and may have thoughts on this!
Can also refer you to Brandon (if you’re at the hackathon), whose got lots of expertise
s
Sean Durkin
04/16/2023, 4:33 PM
Heading over, be there in ~30 min
👍 1
a
Andreas Klintberg
04/16/2023, 5:03 PM
you might want to take a look at https://modal.com they have some examples running huggingface models (it's basically serverless gpus)
s
Sean Durkin
04/16/2023, 6:12 PM
This looks great, Andreas. Got put on the wait list but will circle back to it for future projects
@Aqeel Ali Do you have Nadar's handle? Trying to get past their $5/hr limit for new accounts