HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Train a LLM from Scratch | Hacker News Reader
Train a LLM from Scratch
github.com
3 points
·
linhns
·
·
1 comment
Open article
Save
View on HN
subtick
·
Curious — how did you handle training stability early on? Was convergence an issue without heavy tuning?
Reply on news.ycombinator.com