Zbib M PRO

zbeeb's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a collection 4 days ago

Exact-Age RL: Verifiable Math Data

Collection

Deduplicated Skywork and DeepScaleR math pools, plus their merged version. Only Math-Verify parser-compatible references. • 3 items • Updated 4 days ago

updated a dataset 4 days ago

zbeeb/Skywork-DeepScaleR-Merged-Verifiable-Dedup

Viewer • Updated 4 days ago • 98.9k • 37

published a dataset 4 days ago

zbeeb/Skywork-DeepScaleR-Merged-Verifiable-Dedup

Viewer • Updated 4 days ago • 98.9k • 37

updated a collection 4 days ago

Exact-Age RL: Verifiable Math Data

Collection

Deduplicated Skywork and DeepScaleR math pools, plus their merged version. Only Math-Verify parser-compatible references. • 3 items • Updated 4 days ago

updated a dataset 4 days ago

zbeeb/DeepScaleR-Verifiable-Dedup

Viewer • Updated 4 days ago • 37.7k • 38

published a dataset 4 days ago

zbeeb/DeepScaleR-Verifiable-Dedup

Viewer • Updated 4 days ago • 37.7k • 38

updated a collection 4 days ago

Exact-Age RL: Verifiable Math Data

Collection

Deduplicated Skywork and DeepScaleR math pools, plus their merged version. Only Math-Verify parser-compatible references. • 3 items • Updated 4 days ago

updated a dataset 4 days ago

zbeeb/Skywork-OR1-Math-Verifiable-Dedup

Viewer • Updated 4 days ago • 97.8k • 42

published a dataset 4 days ago

zbeeb/Skywork-OR1-Math-Verifiable-Dedup

Viewer • Updated 4 days ago • 97.8k • 42

updated a collection 6 days ago

Staleness: GRPO Models & Data

Collection

GRPO checkpoints organized by staleness cap, with the shared 17,005-row DAPO math dataset, provenance and benchmark scores. • 11 items • Updated 6 days ago

updated a model 6 days ago

zbeeb/Qwen2.5-Math-7B-GRPO-Staleness-4

Text Generation • 8B • Updated 6 days ago • 109

published a model 6 days ago

zbeeb/Qwen2.5-Math-7B-GRPO-Staleness-4

Text Generation • 8B • Updated 6 days ago • 109

updated a collection 8 days ago

Staleness: GRPO Models & Data

Collection

GRPO checkpoints organized by staleness cap, with the shared 17,005-row DAPO math dataset, provenance and benchmark scores. • 11 items • Updated 6 days ago

updated a model 8 days ago

zbeeb/Qwen2.5-3B-GRPO-Staleness-6

Text Generation • 3B • Updated 8 days ago • 218

published a model 8 days ago

zbeeb/Qwen2.5-3B-GRPO-Staleness-6

Text Generation • 3B • Updated 8 days ago • 218

updated a collection 9 days ago

Staleness: GRPO Models & Data

Collection

GRPO checkpoints organized by staleness cap, with the shared 17,005-row DAPO math dataset, provenance and benchmark scores. • 11 items • Updated 6 days ago

updated a model 9 days ago

zbeeb/Qwen2.5-3B-GRPO-Staleness-8

Text Generation • 3B • Updated 9 days ago • 189

published a model 9 days ago

zbeeb/Qwen2.5-3B-GRPO-Staleness-8

Text Generation • 3B • Updated 9 days ago • 189

updated a collection 9 days ago

Staleness: GRPO Models & Data

Collection

GRPO checkpoints organized by staleness cap, with the shared 17,005-row DAPO math dataset, provenance and benchmark scores. • 11 items • Updated 6 days ago

updated a model 9 days ago

zbeeb/Qwen2.5-Math-1.5B-GRPO-Staleness-8

Text Generation • 2B • Updated 9 days ago • 289