Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings
2024-01-16
· ICLR 2024 poster ·
anchor
Findings
IC-626
Llama 7B retains 95% of its common sense reasoning performance when compressed to 2 GB using JLCM
IC-627
ResNet 18 and ViT B/16 retain significant ImageNet accuracy at 2–3 bit weight compression via JLCM