Effective Long-Context Scaling of Foundation Models

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.

Download the Paper


Written by

Wenhan Xiong

Igor Molybog

Hejia Zhang

Praj Bhargava

Rui Hou

Louis Martin

Rashi Rungta

Karthik Abinav Sankararaman

Barlas Oguz

Madian Khabsa

Han Fang

Yashar Mehdad

Sharan Narang

Kshitiz Malik

Angela Fan

Shruti Bhosale

Sergey Edunov

Mike Lewis

Sinong Wang

Hao Ma

Jingyu Liu



Related Publications

April 14, 2024



CoLLD: Contrastive Layer-to-Layer Distillation for Compressing Multilingual Pre-Trained Speech Encoders

Heng-Jui Chang, Ning Dong (AI), Ruslan Mavlyutov, Sravya Popuri, Andy Chung

April 14, 2024

February 21, 2024



Watermarking Makes Language Models Radioactive

Tom Sander, Pierre Fernandez, Alain Durmus, Matthijs Douze, Teddy Furon

February 21, 2024

December 07, 2023



Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Hakan Inan, Kartikeya Upasani, Jianfeng Chi, Rashi Rungta, Krithika Iyer, Yuning Mao, Davide Testuggine, Madian Khabsa

December 07, 2023

December 06, 2023


Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings

Mattia Atzeni, Mike Plekhanov, Frederic Dreyer, Nora Kassner, Simone Merello, Louis Martin, Nicola Cancedda

December 06, 2023

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.