liang's picture

liang

CharlesLi

·

AI & ML interests

Trustworthy Machine Learning

Recent Activity

liked a Space 1 day ago

aminediroHF/trainer-generator-bf16-mismatch

new activity 5 months ago

deepcs233/Visual-CoT:Not compatible with HF Datasets

upvoted a paper 7 months ago

LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs

View all activity

Organizations

None yet

liked a Space 1 day ago

Defeating the trainer-generator precision mismatch in TRL

Download research PDF (Pro access required)

liked a model about 1 year ago

Qwen/Qwen2.5-3B-Instruct

Text Generation • 3B • Updated Sep 25, 2024 • 9.7M • • 452

liked a dataset about 1 year ago

CharlesLi/graph_hard

Viewer • Updated Apr 22, 2025 • 102k • 6 • 1

liked 2 models over 1 year ago

deepseek-ai/DeepSeek-R1

Text Generation • 685B • Updated Mar 27, 2025 • 3.84M • • 13.3k

Qwen/QwQ-32B-Preview

Text Generation • 33B • Updated Jan 12, 2025 • 9.3k • • 1.74k