Cite
Notes
Only stored in your browser.
Attribution
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
arXiv 2024
Llama 2: Open Foundation and Fine-Tuned Chat Models
arXiv 2023
from 2 papers
Adina Williams
Ahmed A Aly
Ahmed Roman
Akshat Shrivastava
Alan Schelten
Amjad Almahairi
Anas Mahmoud
Andrew Poulton
Angela Fan
Anthony Hartshorn