Liang0223/Qwen-2.5-Math-7B-SFT
8B • Updated • 4
Yongliang Wu
Liang0223
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning upvoted a paper about 6 hours ago
GEditBench v2: A Human-Aligned Benchmark for General Image Editing submitted a paper about 6 hours ago
GEditBench v2: A Human-Aligned Benchmark for General Image EditingOrganizations
None yet
Liang0223/Qwen-2.5-Math-1.5B-SFT
2B • Updated • 5
Liang0223/M-SFT-RL-50
4B • Updated • 1
Liang0223/M-SFT-RL-25
4B • Updated
Liang0223/M-DFT-RL-50
4B • Updated
Liang0223/M-DFT-RL-25
4B • Updated
Liang0223/Qwen-2.5-Math-1.5B-DPO
Text Generation • 2B • Updated • 2 • 1
Liang0223/Qwen2.5-VL-3B-Instruct-SFT
Image-Text-to-Text • 4B • Updated • 1
Liang0223/Qwen2.5-VL-3B-Instruct-DFT
Image-Text-to-Text • 4B • Updated
Liang0223/Qwen-2.5-Math-7B-DFT
8B • Updated • 3 • 1
Liang0223/Qwen-2.5-Math-1.5B-DFT
2B • Updated • 15 • 1