GRPO checkpoints organized by staleness cap, with the shared 17,005-row DAPO math dataset, provenance and benchmark scores.
🏝️ On Vacation
Mohamad Zbib
zbeeb
AI & ML interests
KAUST - AUB
Recent Activity
updated a collection about 14 hours ago
Staleness: GRPO Models & Data updated a model about 14 hours ago
zbeeb/Qwen2.5-Math-7B-GRPO-Staleness-4 published a model about 14 hours ago
zbeeb/Qwen2.5-Math-7B-GRPO-Staleness-4Organizations
models 27
zbeeb/Qwen2.5-Math-7B-GRPO-Staleness-4
Text Generation • 8B • Updated • 105
zbeeb/Qwen2.5-3B-GRPO-Staleness-6
Text Generation • 3B • Updated • 215
zbeeb/Qwen2.5-3B-GRPO-Staleness-8
Text Generation • 3B • Updated • 186
zbeeb/Qwen2.5-Math-1.5B-GRPO-Staleness-8
Text Generation • 2B • Updated • 286
zbeeb/Qwen2.5-3B-GRPO-Staleness-4
Text Generation • 3B • Updated • 318
zbeeb/Qwen2.5-Math-1.5B-GRPO-Staleness-6
Text Generation • 2B • Updated • 352
zbeeb/Qwen2.5-Math-1.5B-GRPO-Staleness-4
Text Generation • 2B • Updated • 178
zbeeb/Qwen2.5-Math-7B-GRPO-Staleness-2
Text Generation • 8B • Updated • 438
zbeeb/Qwen2.5-3B-GRPO-Staleness-2
Text Generation • 3B • Updated • 443
zbeeb/Qwen2.5-Math-1.5B-GRPO-Staleness-2
Text Generation • 2B • Updated • 427
datasets 9
zbeeb/Staleness-GRPO-DAPO-Math-17k
Viewer • Updated • 17k • 66
zbeeb/dapo-math-17k-qwen3-clean
Viewer • Updated • 17k • 27
zbeeb/beneficial-dpo-dataset
Viewer • Updated • 10k • 33
zbeeb/TAPS-Datasets
Viewer • Updated • 210k • 38 • 4
zbeeb/mixeddatasafety7030
Viewer • Updated • 10k • 4
zbeeb/llama3_MathInstruct_data
Updated • 3
zbeeb/unsafe
Viewer • Updated • 200 • 5
zbeeb/safe
Updated • 15
zbeeb/Benign
Updated • 2