News for hackers. Stuff that matters.
Re:CS336: Language Modeling from Scratch by _0ffh on Monday June 01, 2026 @01:51PM (#48360254)
You're right to be sceptical. I have trained reasonably good SLMs for the TinyStories dataset on my 4060Ti (16GB) with no problems. You'll only encounter problems if you want to try if your ideas scale up to models any bigger than "arguably tiny".

There are no comments on this comment yet.