Picture for Diana Liskovich

Diana Liskovich

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Apr 29, 2024
Figure 1 for LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Figure 2 for LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Figure 3 for LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Figure 4 for LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Viaarxiv icon

Llama 2: Open Foundation and Fine-Tuned Chat Models

Add code
Jul 19, 2023
Figure 1 for Llama 2: Open Foundation and Fine-Tuned Chat Models
Figure 2 for Llama 2: Open Foundation and Fine-Tuned Chat Models
Figure 3 for Llama 2: Open Foundation and Fine-Tuned Chat Models
Figure 4 for Llama 2: Open Foundation and Fine-Tuned Chat Models
Viaarxiv icon

A Theory on Adam Instability in Large-Scale Machine Learning

Apr 25, 2023
Figure 1 for A Theory on Adam Instability in Large-Scale Machine Learning
Figure 2 for A Theory on Adam Instability in Large-Scale Machine Learning
Figure 3 for A Theory on Adam Instability in Large-Scale Machine Learning
Figure 4 for A Theory on Adam Instability in Large-Scale Machine Learning
Viaarxiv icon

Simple Local Attentions Remain Competitive for Long-Context Tasks

Add code
Dec 14, 2021
Figure 1 for Simple Local Attentions Remain Competitive for Long-Context Tasks
Figure 2 for Simple Local Attentions Remain Competitive for Long-Context Tasks
Figure 3 for Simple Local Attentions Remain Competitive for Long-Context Tasks
Figure 4 for Simple Local Attentions Remain Competitive for Long-Context Tasks
Viaarxiv icon