September 27, 2023
We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our model series are built through continual pretraining from LLAMA 2 with longer training sequences and on a dataset where long texts are upsampled. We perform extensive evaluation on language modeling, synthetic context probing tasks, and a wide range of research benchmarks. On research benchmarks, our models achieve consistent improvements on most regular tasks and significant improvements on long-context tasks over LLAMA 2. Notably, with a cost-effective instruction tuning procedure that does not require human-annotated long instruction data, the 70B variant can already surpass gpt-3.5-turbo-16k’s overall performance on a suite of long-context tasks. Alongside these results, we provide an in-depth analysis on the individual components of our method. We delve into LLAMA’s position encodings and discuss its limitation in modeling long dependencies. We also examine the impact of various design choices in the pretraining process, including the data mix and the training curriculum of sequence lengths – our ablation experiments suggest that having abundant long texts in the pretrain dataset is not the key to achieving strong performance, and we empirically verify that long context continual pretraining is more efficient and similarly effective compared to pretraining from scratch with long sequences.
Written by
Wenhan Xiong
Igor Molybog
Hejia Zhang
Prajjwal Bhargava
Rui Hou
Rashi Rungta
Yashar Mehdad
Sharan Narang
Kshitiz Malik
Jingyu Liu
Publisher
Meta
Research Topics
November 30, 2023
Xutai Ma, Anna Sun, Hirofumi Inaguma, Paden Tomasello, Siqi Ouyang
November 30, 2023
November 30, 2023
Seamless Communication, Loïc Barrault, Yu-An Chung, Mariano Coria Meglioli, David Dale, Ning Dong, Mark Duppenthaler, Paul-Ambroise Duquenne, Brian Ellis, Hady Elsahar, Justin Haaheim, John Hoffman, Min-Jae Hwang, Hirofumi Inaguma, Christopher Klaiber, Ilia Kulikov, Pengwei Li, Daniel Licht, Jean Maillard, Ruslan Mavlyutov, Alice Rakotoarison, Kaushik Ram Sadagopan, Abinesh Ramakrishnan, Tuan Tran, Guillaume Wenzek, Yilin Yang, Ethan Ye, Ivan Evtimov, Pierre Fernandez, Cynthia Gao, Prangthip Hansanti, Elahe Kalbassi, Amanda Kallet, Artyom Kozhevnikov, Gabriel Mejia Gonzalez, Robin San Roman, Christophe Touret, Corinne Wong, Carleigh Wood, Bokai Yu, Pierre Andrews, Can Balioglu, Peng-Jen Chen, Marta R. Costa-jussà, Maha Elbayad, Hongyu Gong, Francisco Guzmán, Kevin Heffernan, Somya Jain, Justine Kao, Ann Lee, Xutai Ma, Alexandre Mourachko, Benjamin Peloquin, Juan Pino, Sravya Popuri, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Anna Sun, Paden Tomasello, Changhan Wang, Jeff Wang, Skyler Wang, Mary Williamson
November 30, 2023
November 29, 2023
Paul-Ambroise Duquenne, Kevin Heffernan, Alexandre Mourachko, Holger Schwenk, Benoit Sagot (INRIA)
November 29, 2023
November 06, 2023
David Esiobu, Ellen Tan, Saghar Hosseini, Megan Ung, Yuchen Zhang, Jude Fernandes, Jane Yu, Eleonora Presani, Adina Williams, Eric Smith
November 06, 2023
Who We Are
Our Actions
Newsletter