Boris Hanin
@borishanin
Assistant Professor at Princeton ORFE
ID: 2582394438
http://hanin.princeton.edu 22-06-2014 15:29:20
1,1K Tweet
1,1K Followers
286 Following
Pretraining large-depth transformers just got easier! 🚀 HP transfer across model scale ⚡ Compute-efficient pretraining. Super cool collab with Nolan Dey Claire Zhang Mufan Li Cengiz Pehlevan Shane Bergsma Boris Hanin Joel Hastness Cerebras
Essential context — The Stanford Review has been doing important reporting for a long time
Excited to hear Raviraj Jain lead a discussion of funding in AI for Science this Friday!
New NanoGPT training speed record: 3.28 FineWeb val loss in 2.990 minutes on 8xH100 Previous record: 3.014 minutes (1.44s slower) Changelog: Accelerated gradient all-reduce New record-holders: Konstantin Willeke et al. of The Enigma project
Sulaiman Ahmed You are so insanely stupid
Suleiman has been one of the top misinformation purveyors since 10/7 He regularly featured in Mario Nawfal’s in the beginning of the conflict Here he’s caught posting a video that includes an Imperial Star Destroyer This is the level of stupidity we’ve had to deal with
I’m not big on identities, but I am extremely proud to be American. This is true every day, but especially today—I firmly believe this is the greatest country ever on Earth. The American miracle stands alone in world history. I believe in techno-capitalism. We should encourage