1 citations · 1 across the 4 of their papers we have counts for
4 papers
ReALLM: A general framework for LLM compression and fine-tuning
Louis Leconte, Lisa Bedin, Van Minh Nguyen +1
We introduce ReALLM, a novel approach for compression and memory-efficient adaptation of pre-trained language models that encompasses most of the post-training quantization and fin…
BOLD: Boolean Logic Deep Learning
Van Minh Nguyen, Cristian Ocampo, Aymen Askri +2
Deep learning is computationally intensive, with significant efforts focused on reducing arithmetic complexity, particularly regarding energy consumption dominated by data movement…
Queuing dynamics of asynchronous Federated Learning
Louis Leconte, Matthieu Jonckheere, Sergey Samsonov +1
We study asynchronous federated learning mechanisms with nodes having potentially different computational speeds. In such an environment, each node is allowed to work on models wit…
Boolean Logic as an Error feedback mechanism
Louis Leconte
The notion of Boolean logic backpropagation was introduced to build neural networks with weights and activations being Boolean numbers. Most of computations can be done with Boolea…