Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
Paper
• 2309.05516 • Published
• 11
He, Xin
xinhe
AI & ML interests
None yet
Recent Activity
new activity
about 17 hours ago
INC4AI/Step-3.5-Flash-int4-AutoRound:Garbage output? published
a model about 18 hours ago
Intel/Step-3.5-Flash-int4-mixed-AutoRound updated
a model about 19 hours ago
Intel/Step-3.5-Flash-int4-mixed-AutoRound Organizations
authored a paper over 2 years ago