使用Player FM应用程序离线!
Quantizing Transformers by Helping Attention Heads Do Nothing with Markus Nagel - #663
Manage episode 391762946 series 2355587
Today we’re joined by Markus Nagel, research scientist at Qualcomm AI Research, who helps us kick off our coverage of NeurIPS 2023. In our conversation with Markus, we cover his accepted papers at the conference, along with other work presented by Qualcomm AI Research scientists. Markus’ first paper, Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing, focuses on tackling activation quantization issues introduced by the attention mechanism and how to solve them. We also discuss Pruning vs Quantization: Which is Better?, which focuses on comparing the effectiveness of these two methods in achieving model weight compression. Additional papers discussed focus on topics like using scalarization in multitask and multidomain learning to improve training and inference, using diffusion models for a sequence of state models and actions, applying geometric algebra with equivariance to transformers, and applying a deductive verification of chain of thought reasoning performed by LLMs.
The complete show notes for this episode can be found at twimlai.com/go/663.
710集单集
Quantizing Transformers by Helping Attention Heads Do Nothing with Markus Nagel - #663
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Manage episode 391762946 series 2355587
Today we’re joined by Markus Nagel, research scientist at Qualcomm AI Research, who helps us kick off our coverage of NeurIPS 2023. In our conversation with Markus, we cover his accepted papers at the conference, along with other work presented by Qualcomm AI Research scientists. Markus’ first paper, Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing, focuses on tackling activation quantization issues introduced by the attention mechanism and how to solve them. We also discuss Pruning vs Quantization: Which is Better?, which focuses on comparing the effectiveness of these two methods in achieving model weight compression. Additional papers discussed focus on topics like using scalarization in multitask and multidomain learning to improve training and inference, using diffusion models for a sequence of state models and actions, applying geometric algebra with equivariance to transformers, and applying a deductive verification of chain of thought reasoning performed by LLMs.
The complete show notes for this episode can be found at twimlai.com/go/663.
710集单集
すべてのエピソード
×欢迎使用Player FM
Player FM正在网上搜索高质量的播客,以便您现在享受。它是最好的播客应用程序,适用于安卓、iPhone和网络。注册以跨设备同步订阅。