Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models
Paper
•
2309.15531
•
Published
•
1
token-frequency
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
token-frequency's activity
PenPaperKeyCode
authored
5
papers
about 5 hours ago
HyperCLOVA X Technical Report
Paper
•
2404.01954
•
Published
•
25
Peri-LN: Revisiting Layer Normalization in the Transformer Architecture
Paper
•
2502.02732
•
Published
•
1
AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models
Paper
•
2210.03858
•
Published
LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
Paper
•
2206.09557
•
Published
PenPaperKeyCode
authored
a
paper
almost 2 years ago