Hugging Face's logo
Elie Bakouch's picture
1 6 12

Elie Bakouch

eliebak
21world's profile picture kamilakesbi's profile picture RaphaelCarton's profile picture
·
eliebakk
eliebak

AI & ML interests

Training LLM's @ 🤗

Organizations

Hugging Face's profile picture HuggingFaceBR4's profile picture Hugging Face TB Research's profile picture huggingPartyParis's profile picture HuggingFaceFW's profile picture Nanotron Research's profile picture Hugging Face SMOL's profile picture

Posts 1

view post
Post
620
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

Collections 2

Papers 1