157 citations · 387 across the 15 of their papers we have counts for
18 papers
A Holistic Assessment of the Carbon Footprint of Noor, a Very Large Arabic Language Model
Imad Lakim, Ebtesam Almazrouei, Ibrahim Abu Alhaol +2
As ever larger language models grow more ubiquitous, it is crucial to consider their environmental impact. Characterised by extreme size and resource use, recent generations of mod…
Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment
Ziao Wang, Kilian Müller, Matthew Filipovich +12
Modern deep learning relies nearly exclusively on dedicated electronic hardware accelerators. Photonic approaches, with low consumption and high operation speed, are increasingly c…
The Falcon Series of Open Language Models
Ebtesam Almazrouei, Hamza Alobeidli, Abdulaziz Alshamsi +11
We introduce the Falcon series: 7B, 40B, and 180B parameters causal decoder-only models trained on a diverse high-quality corpora predominantly assembled from web data. The largest…
The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only
Guilherme Penedo, Quentin Malartic, Daniel Hesslow +6
Large language models are commonly trained on a mixture of filtered web data and curated high-quality corpora, such as social media conversations, books, or technical papers. This…
What Language Model to Train if You Have One Million GPU Hours?
Teven Le Scao, Thomas Wang, Daniel Hesslow +16
The crystallization of modeling methods around the Transformer architecture has been a boon for practitioners. Simple, well-motivated architectural variations can transfer across t…
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
BigScience Workshop, :, Teven Le Scao +391
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to wi…
Scaling Laws Beyond Backpropagation
Matthew J. Filipovich, Alessandro Cappelli, Daniel Hesslow +1
Alternatives to backpropagation have long been studied to better understand how biological brains may learn. Recently, they have also garnered interest as a way to train neural net…
What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?
Thomas Wang, Adam Roberts, Daniel Hesslow +5
Large pretrained Transformer language models have been shown to exhibit zero-shot generalization, i.e. they can perform a wide variety of tasks that they were not explicitly traine…
PAGnol: An Extra-Large French Generative Model
Julien Launay, Elena Tommasone, Baptiste Pannier +5
Access to large pre-trained models of varied architectures, in many different languages, is central to the democratization of NLP. We introduce PAGnol, a collection of French GPT m…
Is the Number of Trainable Parameters All That Actually Matters?
Amélie Chatelain, Amine Djeghri, Daniel Hesslow +2
Recent work has identified simple empirical scaling laws for language models, linking compute budget, dataset size, model size, and autoregressive modeling loss. The validity of th…
LightOn Optical Processing Unit: Scaling-up AI and HPC with a Non von Neumann co-processor
Charles Brossollet, Alessandro Cappelli, Igor Carron +14
We introduce LightOn's Optical Processing Unit (OPU), the first photonic AI accelerator chip available on the market for at-scale Non von Neumann computations, reaching 1500 TeraOP…
ROPUST: Improving Robustness through Fine-tuning with Photonic Processors and Synthetic Gradients
Alessandro Cappelli, Julien Launay, Laurent Meunier +2
Robustness to adversarial attacks is typically obtained through expensive adversarial training with Projected Gradient Descent. Here we introduce ROPUST, a remarkably simple and ef…
Photonic Differential Privacy with Direct Feedback Alignment
Ruben Ohana, Hamlet J. Medina Ruiz, Julien Launay +4
Optical Processing Units (OPUs) -- low-power photonic chips dedicated to large scale random projections -- have been used in previous work to train deep neural networks using Direc…
Adversarial Robustness by Design through Analog Computing and Synthetic Gradients
Alessandro Cappelli, Ruben Ohana, Julien Launay +3
We propose a new defense mechanism against adversarial attacks inspired by an optical co-processor, providing robustness without compromising natural accuracy in both white-box and…
Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment
Julien Launay, Iacopo Poli, Kilian Müller +5
The scaling hypothesis motivates the expansion of models past trillions of parameters as a path towards better performance. Recent significant developments, such as GPT-3, have bee…
Light-in-the-loop: using a photonics co-processor for scalable training of neural networks
Julien Launay, Iacopo Poli, Kilian Müller +4
As neural networks grow larger and more complex and data-hungry, training costs are skyrocketing. Especially when lifelong learning is necessary, such as in recommender systems or…
Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures
Julien Launay, Iacopo Poli, François Boniface +1
Despite being the workhorse of deep learning, the backpropagation algorithm is no panacea. It enforces sequential layer updates, thus preventing efficient parallelization of the tr…
Principled Training of Neural Networks with Direct Feedback Alignment
Julien Launay, Iacopo Poli, Florent Krzakala
The backpropagation algorithm has long been the canonical training method for neural networks. Modern paradigms are implicitly optimized for it, and numerous guidelines exist to en…