How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study
Paper
•
2404.14047
•
Published
•
45
•
12
Haotong Qin
HaotongQin
AI & ML interests
Model Compression, Efficient AIGC
Recent Activity
authored
a paper
25 days ago
How Good is Google Bard's Visual Understanding? An Empirical Study on
Open Challenges
authored
a paper
25 days ago
Accurate LoRA-Finetuning Quantization of LLMs via Information Retention
authored
a paper
25 days ago
BiBERT: Accurate Fully Binarized BERT
Organizations
HaotongQin's activity
commented
a
paper
9 months ago