🔄 In a Training Loop
haodi lei
bingyang-lei
AI & ML interests
None yet
Recent Activity
upvoted a paper about 16 hours ago
TPPO: Tracking-Value PPO For Language Model Reasoning upvoted a paper 28 days ago
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening upvoted a paper about 1 month ago
Rethinking On-Policy Distillation of Large Language Models II: One Training ExampleOrganizations
-
bingyang-lei/Qwen3-8B-Ins-Draft-OPD
Text Generation • 1B • Updated • 149 -
bingyang-lei/Qwen3-4B-Ins-Draft-OPD
Text Generation • 0.5B • Updated • 45 • 2 -
bingyang-lei/Qwen3-30B-A3B-Thinking-2507-Draft-OPD
Text Generation • 0.5B • Updated • 34 • 1 -
bingyang-lei/Qwen3-4B-Thinking-Draft-OPD
Text Generation • 0.5B • Updated • 32
-
bingyang-lei/Qwen3-8B-Ins-Draft-OPD
Text Generation • 1B • Updated • 149 -
bingyang-lei/Qwen3-4B-Ins-Draft-OPD
Text Generation • 0.5B • Updated • 45 • 2 -
bingyang-lei/Qwen3-30B-A3B-Thinking-2507-Draft-OPD
Text Generation • 0.5B • Updated • 34 • 1 -
bingyang-lei/Qwen3-4B-Thinking-Draft-OPD
Text Generation • 0.5B • Updated • 32
models 21
bingyang-lei/qwen3-4b-eagle3-thinking-draftopd
0.2B • Updated • 17
bingyang-lei/qwen3-4b-eagle3-thinking-baseline
0.2B • Updated • 9
bingyang-lei/qwen3-8b-thinking-dflash-draftopd-tvloss
1B • Updated • 24
bingyang-lei/dflash-qwen3-8b-thinking
1B • Updated • 20
bingyang-lei/Intern-S2-Preview-SimpleOPD
Image-Text-to-Text • 36B • Updated • 19 • 1
bingyang-lei/Qwen3.5-35B-A3B-SimpleOPD
Image-Text-to-Text • 36B • Updated • 23 • 1
bingyang-lei/data-scale-20000step-qwen3-4b-think-draft-opd
Updated
bingyang-lei/data-scale-17500step-qwen3-4b-think-draft-opd
0.5B • Updated • 5
bingyang-lei/data-scale-15000step-qwen3-4b-draft-opd
0.5B • Updated • 11
bingyang-lei/data-scale-12500step-qwen3-4b-draft-opd
0.5B • Updated • 9
datasets 0
None public yet