RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
Paper
•
2503.01820
•
Published
•
2
•
3
Yi-Lin Sung
a2889184
AI & ML interests
None yet
Recent Activity
authored
a paper
4 days ago
Unified Coarse-to-Fine Alignment for Video-Text Retrieval
authored
a paper
4 days ago
Merge, Then Compress: Demystify Efficient SMoE with Hints from Its
Routing Policy
authored
a paper
4 days ago
ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language
Models
Organizations
None yet
a2889184's activity
commented
a
paper
4 days ago
Can someone reproduce the accuracy of Llama 3.1 models?
2
#11 opened 8 months ago
by
damoict
Can someone reproduce the accuracy of Llama 3.1 models?
2
#11 opened 8 months ago
by
damoict