wenhua cheng's picture

wenhua cheng

wenhuach

·

wenhuach21

AI & ML interests

Model Compression, CV

Recent Activity

new activity 11 days ago

Intel/gemma-4-31B-it-int4-AutoRound:This quant is the best. Please conver it to GGUF

updated a model 11 days ago

Intel/gemma-4-31B-it-q4km-AutoRound-preview

published a model 11 days ago

Intel/gemma-4-31B-it-q4km-AutoRound-preview

View all activity

Organizations

authored a paper 7 months ago

SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

Paper • 2512.04746 • Published Dec 4, 2025 • 14

authored a paper over 2 years ago

TEQ: Trainable Equivalent Transformation for Quantization of LLMs

Paper • 2310.10944 • Published Oct 17, 2023 • 10

authored a paper almost 3 years ago

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs

Paper • 2309.05516 • Published Sep 11, 2023 • 12