HackerTrans
TopNewTrendsCommentsPastAskShowJobs

prjkt

5 karmajoined 6 tahun yang lalu

comments

prjkt
·5 jam yang lalu·discuss
It's like Microsoft banning Vim users that use Azure
prjkt
·11 jam yang lalu·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 bulan yang lalu·discuss
In that case, what tokenizer version? What was the temperature set to? topk? topp? FP32? FP16? Quantized? Hopper? Blackwell?