Viewing profile — VictorSh

VictorSh

HN member

No profile information was provided.

comment
Comment #28913002
(author here) That's an interesting take (which I agree with). Providing a quick way to stress test the model is definitely a double edge sword. One one hand it increases engagemen…

Mon, Oct 18, 2021, 11:11 PM UTC
comment
Comment #28912807
(author here) I don't have exact numbers for latency but the inference widget is currently on a TPU v3-8 (which if I am not mistaken could roughly be compared to a cluster of 8 V10…

Mon, Oct 18, 2021, 10:49 PM UTC
comment
Comment #28906369
Yes! -> https://huggingface.co/bigscience/T0pp

Mon, Oct 18, 2021, 3:23 PM UTC
story
Long-range transformers in NLP: existing approaches, assumptions and trade-offs
Tue, Mar 09, 2021, 7:44 PM UTC