412 citations · 698 across the 17 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 3 cited
FP8-LM: Training FP8 Large Language Models
Houwen Peng, Kan Wu, Yixuan Wei +17
In this paper, we explore FP8 low-bit data formats for efficient training of large language models (LLMs). Our key insight is that most variables, such as gradients and optimizer s…
cs.CV2023★ 1 cited
Human Pose as Compositional Tokens
Zigang Geng, Chunyu Wang, Yixuan Wei +3
Human pose is typically represented by a coordinate vector of body joints or their heatmap embeddings. While easy for data processing, unrealistic pose estimates are admitted due t…