ZClip: Adaptive Spike Mitigation for LLM Pre-Training
Paper • 2504.02507 • Published • 88
Abhay kumar
akanyaani
AI & ML interests
LLMs, GenAI, Transformers
Recent Activity
liked a model 4 days ago
Rta-AILabs/Nandi-Mini-150M upvoted an article 2 months ago
Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMs liked a Space 3 months ago
tiiuae/tiny-h1-blogpostOrganizations
authored 4
papers about 1 year ago