Y
Hacker News
new
|
ask
|
show
|
jobs
by
jncraton
1087 days ago
OpenLLaMA models up to 13B parameters have now been trained on 1T tokens:
https://github.com/openlm-research/open_llama
1 comments
underlines
1087 days ago
unfortunately not openllama-33b yet
link
emadm
1087 days ago
20b done
link