Zürich

Antoni-Joan Solergibert

Advanced
@TJ-Solergibert

Research Engineer @eth-ai-center - LLM Training at scale! tj.solergibert@gmail.com

tj-solergibert.github.io

transformers-in-supercomputers. Transformers training in a supercomputer with the 🤗 Stack and Slurm

15

MN5-Distributed-PyTorch. Entry point for developing distributed applications with PyTorch, Slurm and Singularity on MareNostrum5 Supercomputer

3

Megatron-LM-In-Depth. Debugging Megatron. 3D Parallelism, models, training and more!

3
3
Apply