HackerTrans
TopNewTrendsCommentsPastAskShowJobs

prjkt

6 karmajoined 6 yıl önce

comments

prjkt
·15 dakika önce·discuss
It's like Microsoft banning Vim users that use Azure
prjkt
·6 saat önce·discuss
> If there's such a dramatic hole in demand, who are NVIDIA selling their compute to?

NVIDIA itself is also training foundation models (and open-sourcing them). If there is excess compute available, NVIDIA can increase the scale of such models.
prjkt
·4 ay önce·discuss
In that case, what tokenizer version? What was the temperature set to? topk? topp? FP32? FP16? Quantized? Hopper? Blackwell?