-
First-Order Error Matters: Accurate Compensation for Quantized Large Language Models
Paper • 2507.11017 • Published • 1 -
Xingyu-Zheng/Qwopus3.5-9B-v3-INT8-FOEM
Image-Text-to-Text • 9B • Updated • 2 -
Xingyu-Zheng/Qwopus3.5-9B-v3-INT4-FOEM
Image-Text-to-Text • 9B • Updated • 23 -
Xingyu-Zheng/Qwopus3.5-27B-v3-INT8-FOEM
Image-Text-to-Text • 27B • Updated • 2
Xingyu Zheng
Xingyu-Zheng
AI & ML interests
None yet
Recent Activity
new activity about 2 months ago
Xingyu-Zheng/Qwopus3.6-27B-v1-preview-INT4-FOEM:Improved quality by changing the chat_template.jinja updated a model about 2 months ago
Xingyu-Zheng/Qwopus3.6-27B-v1-preview-INT4-FOEM new activity about 2 months ago
Xingyu-Zheng/Qwen3.6-27B-INT8-FOEM:MTP not accepting tokensOrganizations
-
First-Order Error Matters: Accurate Compensation for Quantized Large Language Models
Paper • 2507.11017 • Published • 1 -
Xingyu-Zheng/Qwopus3.5-9B-v3-INT8-FOEM
Image-Text-to-Text • 9B • Updated • 2 -
Xingyu-Zheng/Qwopus3.5-9B-v3-INT4-FOEM
Image-Text-to-Text • 9B • Updated • 23 -
Xingyu-Zheng/Qwopus3.5-27B-v3-INT8-FOEM
Image-Text-to-Text • 27B • Updated • 2