6 papers
-Parametrization for Mixture of Experts
Jan MaÅaÅnicki, Kamil Ciebiera, Mateusz BoruÅ +8
Recent years have seen a growing interest and adoption of LLMs, with Mixture-of-Experts (MoE) emerging as a leading architecture in extremely large models. Currently, the largest o…
Decoupled Relative Learning Rate Schedules
Jan Ludziejewski, Jan MaÅaÅnicki, Maciej Pióro +8
In this work, we introduce a novel approach for optimizing LLM training by adjusting learning rates across weights of different components in Transformer models. Traditional method…
Projected Compression: Trainable Projection for Efficient Transformer Compression
Maciej Stefaniak, MichaÅ Krutul, Jan MaÅaÅnicki +6
Large language models have steadily increased in size to achieve improved performance; however, this growth has also led to greater inference time and computational demands. Conseq…
Structured Packing in LLM Training Improves Long Context Utilization
Konrad Staniszewski, Szymon Tworkowski, Sebastian Jaszczur +4
Recent advancements in long-context large language models have attracted significant attention, yet their practical applications often suffer from suboptimal context utilization. T…
Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient
Jan Ludziejewski, Maciej Pióro, Jakub Krajewski +8
Mixture of Experts (MoE) architectures have significantly increased computational efficiency in both research and real-world applications of large-scale machine learning models. Ho…
Mixture of Tokens: Continuous MoE through Cross-Example Aggregation
Szymon Antoniak, MichaŠKrutul, Maciej Pióro +7
Mixture of Experts (MoE) models based on Transformer architecture are pushing the boundaries of language and vision tasks. The allure of these models lies in their ability to subst…