ZClip: Adaptive Spike Mitigation for LLM Pre-Training
Paper
• 2504.02507 • Published
• 88
Abhay kumar
akanyaani
AI & ML interests
LLMs, GenAI, Transformers
Recent Activity
upvoted an article 29 days ago
Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMs liked
a Space about 1 month ago
tiiuae/tiny-h1-blogpost upvoted a paper about 2 months ago
Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers Organizations
authored 4 papers 11 months ago