Intel/Step-3.5-Flash-int4-mixed-AutoRound Text Generation • 28B • Updated 43 minutes ago • 204 • 5
Intel/Step-3.5-Flash-int4-mixed-AutoRound Text Generation • 28B • Updated 43 minutes ago • 204 • 5
Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs Paper • 2309.05516 • Published Sep 11, 2023 • 11