The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training
Paper
• 2603.10444 • Published
AI & ML interests
If you are searching chinese NLP pretrained model, Fengshenbang-LM is all your need! NLP, Pretrain models, Big models, Chinese domain, Fengshenbang-LM
Recent Activity
View all activity
xianbao
submitted a paper to Daily Papers about 1 hour ago
wanng
authored 2 papers about 2 months ago
wanng
submitted a paper to Daily Papers about 2 months ago
xianbao
authored a paper 4 months ago
wuxiaojun
authored a paper 6 months ago
wanng
authored 2 papers 6 months ago
wanng
authored 2 papers 7 months ago
关于中文推理数据集
1
#4 opened 9 months ago
by
weiminw
这个IDEA-CCNL/Erlangshen-MegatronBert-1.3B模型有人在本地电脑上微调成功过吗？
4
#1 opened over 3 years ago
by
jikehukai
cannot download model
4
#7 opened 9 months ago
by
JackieTeh70
wanng
authored a paper about 1 year ago
RLSNLP
authored 5 papers about 1 year ago
MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
Paper
• 2311.16502 • Published
• 39
iDesigner: A High-Resolution and Complex-Prompt Following Text-to-Image Diffusion Model for Interior Design
Paper
• 2312.04326 • Published
• 3
Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects
Paper
• 2312.05278 • Published
• 3
Fostering Natural Conversation in Large Language Models with NICO: a Natural Interactive COnversation dataset
Paper
• 2408.09330 • Published
Preference Leakage: A Contamination Problem in LLM-as-a-judge
Paper
• 2502.01534 • Published
• 40
wanng
authored a paper about 1 year ago