INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound Image-Text-to-Text • 234B • Updated Jul 8 • 22
INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound Image-Text-to-Text • 234B • Updated Jul 8 • 22
INCModelSharing/DeepSeek-V4-Pro-DSpark-MXFP4-Mixed-CT-AutoRound Text Generation • 889B • Updated Jun 30 • 17 • 1
INCModelSharing/DeepSeek-V4-Pro-DSpark-MXFP4-Mixed-CT-AutoRound Text Generation • 889B • Updated Jun 30 • 17 • 1
TEQ: Trainable Equivalent Transformation for Quantization of LLMs Paper • 2310.10944 • Published Oct 17, 2023 • 10
Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs Paper • 2309.05516 • Published Sep 11, 2023 • 15