Matched OpenR1 SFT checkpoints and subsequent GRPO models for studying token-level behavior during the transition from SFT to RL.
🏝️ On Vacation
Zbib M
zbeeb
AI & ML interests
KAUST - AUB
Recent Activity
updated a collection about 13 hours ago
OpenR1 SFT to GRPO: Token-Level Study updated a model about 13 hours ago
zbeeb/Qwen2.5-1.5B-Base-GRPO published a model about 13 hours ago
zbeeb/Qwen2.5-1.5B-Base-GRPOOrganizations
models 36
zbeeb/Qwen2.5-1.5B-Base-GRPO
Text Generation • 2B • Updated
zbeeb/Qwen2.5-Math-1.5B-Base-GRPO
Text Generation • 2B • Updated
zbeeb/Qwen2.5-3B-OpenR1-SFT-GRPO
Text Generation • 3B • Updated
zbeeb/Qwen2.5-Math-1.5B-OpenR1-SFT-GRPO
Text Generation • 2B • Updated
zbeeb/Qwen2.5-1.5B-OpenR1-SFT-GRPO
Text Generation • 2B • Updated
zbeeb/Qwen2.5-3B-Instruct-OpenR1-SFT
Text Generation • 3B • Updated
zbeeb/Qwen2.5-3B-OpenR1-SFT
Text Generation • 3B • Updated • 143
zbeeb/Qwen2.5-Math-1.5B-OpenR1-SFT
Text Generation • 2B • Updated • 143
zbeeb/Qwen2.5-1.5B-OpenR1-SFT
Text Generation • 2B • Updated • 142
zbeeb/Qwen2.5-Math-7B-GRPO-Staleness-4
Text Generation • 8B • Updated • 127
datasets 13
zbeeb/OpenR1-SFT-Math-20k
Viewer • Updated • 60.8k • 102
zbeeb/Skywork-DeepScaleR-Merged-Verifiable-Dedup
Viewer • Updated • 98.9k • 40
zbeeb/DeepScaleR-Verifiable-Dedup
Viewer • Updated • 37.7k • 41
zbeeb/Skywork-OR1-Math-Verifiable-Dedup
Viewer • Updated • 97.8k • 50
zbeeb/Staleness-GRPO-DAPO-Math-17k
Viewer • Updated • 17k • 163
zbeeb/dapo-math-17k-qwen3-clean
Viewer • Updated • 17k • 32
zbeeb/beneficial-dpo-dataset
Viewer • Updated • 10k • 34
zbeeb/TAPS-Datasets
Viewer • Updated • 210k • 45 • 4
zbeeb/mixeddatasafety7030
Viewer • Updated • 10k • 7
zbeeb/llama3_MathInstruct_data
Updated • 6