Sandeep is a research manager at NVIDIA. His research is focused on large language model training and alignment. He received an M.Sc. in NLP from Carnegie Mellon University and a Ph.D. in deep learning from the University of Montreal.
Posts by Sandeep Subramanian
Aug 08, 2023
Curating Trillion-Token Datasets: Introducing NVIDIA NeMo Data Curator
The latest developments in large language model (LLM) scaling laws have shown that when scaling the number of model parameters, the number of tokens used for...
8 MIN READ