Chinchilla, every mention
5 scenes · ← back to Chinchilla
tap a year for its mentions
every year anyone Sarah Guo 3Karan Singhal 1Emad Mostaque 1Amjad Masad 1
Verbatim, from the transcripts: the passages where Chinchilla comes up
No Priors Ep. 40 | With Arthur Mensch, CEO Mistral AI
No Priors Ep. 33 | With Replit's CEO & Co-Founder Amjad Masad
- ▶ 13:19 Amjad Masad Yeah, the chinchilla paper first came out and LLAMA had been announced and the idea of just training them longer had just been in the air and, and we're like, okay, what if we, we apply all these open source tokens on a smaller model?
No Priors Ep. 27 | With Sarah Guo & Elad Gil
No Priors Ep. 17 | With Karan Singhal
- ▶ 8:55 Karan Singhal And so this paper, again, found something similar to the Chinchilla paper, which was that the total amount of data being used for these models was relatively, uh, low compared to the number of parameters, and that if we wanted to add in…
No Priors Ep. 3 | With Stability AI’s Emad Mostaque
- ▶ 12:57 Emad Mostaque I think things like the chinchilla paper, uh, that's the sixty-seven billion parameter model that's as performant as GPT-III at one hundred seventy-five billion, are important in that, because it said that training more is important.