HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Comment by amelius | Hacker News Reader
Parent
Full thread
amelius
·
Nor that the training from scratch will even work.
View on HN
tuned
·
exactly, that is the current objective. To proove that generation for a specific domain is on-par with causal attention models
Reply on news.ycombinator.com