Task
Other
E
yuhuili/EAGLE3-LLaMA3.1-Instruct-8B
Other·yuhuili· 317.8K· 10
EAGLE (Extrapolation Algorithm for Greater Language-model Efficiency) is a new baseline for fast decoding of Large Language Models (LLMs) with provable performance maintenance. This approach involves extrapolating the second-top-layer contextual feature vectors of LLMs, enabling a significant boost in generation efficiency.
# pull & run locally
pip install mlforge-sdk && mlforge pull yuhuili/EAGLE3-LLaMA3.1-Instruct-8B
pip install mlforge-sdk && mlforge pull yuhuili/EAGLE3-LLaMA3.1-Instruct-8B
Model details
Provider
yuhuili
Size
1.6 GB
License
apache-2.0
Downloads
317.8K
Likes
10
Paper
arXiv:2401.15077
Updated
2025-09-19
About yuhuili/EAGLE3-LLaMA3.1-Instruct-8B
EAGLE (Extrapolation Algorithm for Greater Language-model Efficiency) is a new baseline for fast decoding of Large Language Models (LLMs) with provable performance maintenance. This approach involves extrapolating the second-top-layer contextual feature vectors of LLMs, enabling a significant boost in generation efficiency.