Elie Bakouch

eliebak

AI & ML interests

Training LLM's @ 🤗

Recent Activity

reacted to cfahlgren1's post with ❤️ about 13 hours ago
upvoted a paper about 18 hours ago
upvoted a paper 6 days ago

Articles

Organizations

Posts 1

view post
Post
1037
Wow, impressive 340B model by nvidia with a nice permissive license! 🚀 The technical report is full of insights and seems to use a different learning rate schedule than cosine, probably a variant of WSD. Hope to get more info on that! 👀

nvidia/nemotron-4-340b-666b7ebaf1b3867caf2f1911