Table of Links Abstract and 1. Introduction Abstract and 1. Introduction 2. Method 2. Method 3. Experiments on real data 3. Experiments on real data 3.1. Benefits scale with model size and 3.2. Faster inference 3.1. Benefits scale with model size and 3.2. Faster inference 3.3. Learning global patterns with multi-byte prediction and 3.4. Searching for the optimal n 3.3. Learning global patterns with multi-byte prediction and 3.4. Searching for the optimal n n 3.5. Training for multiple epochs and 3.6. Finetuning multi-token predictors 3.5. Training for multiple epochs and 3.6. Finetuning multi-token predictors 3.7. Multi-token prediction on natural language 3.7. Multi-token prediction on natural language 4. Ablations on synthetic data and 4.1. Induction capability 4. Ablations on synthetic data and 4.1. Induction capability 4.2. Algorithmic reasoning 4.2. Algorithmic reasoning 5. Why does it work? Some speculation and 5.1. Lookahead reinforces choice points 5. Why does it work? Some speculation and 5.1. Lookahead reinforces choice points 5.2. Information-theoretic argument 5.2. Information-theoretic argument 6. Related work 6. Related work 7. Conclusion, Impact statement, Environmental impact, Acknowledgements, and References 7. Conclusion, Impact statement, Environmental impact, Acknowledgements, and References A. Additional results on self-speculative decoding A. Additional results on self-speculative decoding B. Alternative architectures B. Alternative architectures C. Training speeds C. Training speeds D. Finetuning D. Finetuning E. Additional results on model scaling behavior E. Additional results on model scaling behavior F. Details on CodeContests finetuning F. Details on CodeContests finetuning G. Additional results on natural language benchmarks G. Additional results on natural language benchmarks H. Additional results on abstractive text summarization H. Additional results on abstractive text summarization I. Additional results on mathematical reasoning in natural language I. Additional results on mathematical reasoning in natural language J. Additional results on induction learning J. Additional results on induction learning K. Additional results on algorithmic reasoning K. Additional results on algorithmic reasoning L. Additional intuitions on multi-token prediction L. Additional intuitions on multi-token prediction M. Training hyperparameters M. Training hyperparameters 2. Method Standard language modeling learns about a large text corpus x1, . . . xT by implementing a next-token prediction task. Formally, the learning objective is to minimize the cross-entropy loss In this work, we generalize the above by implementing a multi-token prediction task, where at each position of the training corpus, the model is instructed to predict n future tokens at once. This translates into the cross-entropy loss This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv Authors:
(1) Fabian Gloeckle, FAIR at Meta, CERMICS Ecole des Ponts ParisTech, and contributed equally;
(2) Badr Youbi IdrissiFAIR at Meta, LISN Université Paris-Saclay, and contributed equally;
(3) Baptiste Rozière, FAIR at Meta;
(4) David Lopez-Paz, FAIR at Meta and his the last author;
(5) Gabriel Synnaeve, FAIR at Meta and his the last author. Authors: Authors: (1) Fabian Gloeckle, FAIR at Meta, CERMICS Ecole des Ponts ParisTech, and contributed equally; (2) Badr Youbi IdrissiFAIR at Meta, LISN Université Paris-Saclay, and contributed equally; (3) Baptiste Rozière, FAIR at Meta; (4) David Lopez-Paz, FAIR at Meta and his the last author; (5) Gabriel Synnaeve, FAIR at Meta and his the last author.

Empirical Validation of Multi-Token Prediction for LLMs

Multi-Token Prediction: Higher Sample Efficiency for Large Language Models

How the Most Important Models Actually Work

Too Long; Didn't Read

Get Free Unlimited IP Geo Data With IPinfo Lite

Multi-Token Prediction: Architecture for Memory-Efficient LLM Training

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

A Formalization of the SylloBio-NLI Resource Generation Process

Self-Speculative Decoding Speeds for Multi-Token LLMs

Can Smaller AI Outperform the Giants?

Why The Right AI Backbones Trump Raw Size Every Time

The Artistry Behind Efficient AI Conversations

The Small AI Model Making Big Waves in Vision-Language Intelligence

A Formalization of the SylloBio-NLI Resource Generation Process

Self-Speculative Decoding Speeds for Multi-Token LLMs

Can Smaller AI Outperform the Giants?

Why The Right AI Backbones Trump Raw Size Every Time

The Artistry Behind Efficient AI Conversations

The Small AI Model Making Big Waves in Vision-Language Intelligence

Light-Mode

Classic

Newspaper

Dark-Mode

Neon Noir

Minty

HN StartUps