PyTorch Distributed Debugging Tips
·10 words·1 min
Twitter Post
EMA Tuning
·43 words·1 min
Phi-2: The Most Powerful 2.7B Model Yet
·19 words·1 min
One Percent, One Week
·31 words·1 min
Scaling MLPs Paper
·54 words·1 min
Matmul and Strassen's Algo
·39 words·1 min
LLMs and Planning
·52 words·1 min
Announcement: PhD Internship for LLM Evaluation
·20 words·1 min
Phi-2: Smol but Mighty
·36 words·1 min
Thankuritto
·16 words·1 min