INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound Text Generation • 410B • Updated about 11 hours ago • 12 • 1
INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound Text Generation • 410B • Updated about 11 hours ago • 12 • 1
Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs Paper • 2309.05516 • Published Sep 11, 2023 • 12