but deepseek hasn't claimed the figure touted by everyone for this particular R1... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		anshumankmr 6 months ago \| parent \| context \| favorite \| on: Open-R1: an open reproduction of DeepSeek-R1 but deepseek hasn't claimed the figure touted by everyone for this particular R1 model, cause that 5.6mn was apparently for Deepseek's coder model

boroboro4 6 months ago [–]

5.6mn figure is for base Deepseek V3 model. Both instruction and reasoning tuning of it has neglectable cost in comparison with it.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact