The Stack: 3 TB of permissively licensed source code

The Stack: 3 TB of permissively licensed source code

20 November 2022

Loubna Ben Allal

Carlos Muñoz Ferrandis

Margaret Mitchell

Dzmitry Bahdanau

Leandro von Werra

Papers citing "The Stack: 3 TB of permissively licensed source code"

1 / 51 papers shown

Title
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism M. Shoeybi M. Patwary Raul Puri P. LeGresley Jared Casper Bryan Catanzaro MoE 243 1,815 0 17 Sep 2019