Zbib M PRO

zbeeb's activity

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

authored a paper about 21 hours ago

Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration

Paper • 2608.29378 • Published Aug 29

updated a collection 1 day ago

Easy-Tune: cleaned Math Data

Collection

Deduplicated Skywork and DeepScaleR math pools, plus their merged version. Only Math-Verify parser-compatible references. • 6 items • Updated 1 day ago

updated a dataset 1 day ago

zbeeb/OpenThoughts3-Qwen3-4B-Math-21k

Viewer • Updated 1 day ago • 21.2k • 53

published a dataset 1 day ago

zbeeb/OpenThoughts3-Qwen3-4B-Math-21k

Viewer • Updated 1 day ago • 21.2k • 53

updated a collection 3 days ago

OpenR1 SFT to GRPO: Token-Level Study

Collection

Matched OpenR1 SFT checkpoints and subsequent GRPO models for studying token-level behavior during the transition from SFT to RL. • 14 items • Updated 3 days ago

updated a model 3 days ago

zbeeb/Qwen2.5-3B-Instruct-OpenR1-SFT-GRPO

Text Generation • 3B • Updated 3 days ago • 15

published a model 3 days ago

zbeeb/Qwen2.5-3B-Instruct-OpenR1-SFT-GRPO

Text Generation • 3B • Updated 3 days ago • 15

updated a collection 3 days ago

OpenR1 SFT to GRPO: Token-Level Study

Collection

Matched OpenR1 SFT checkpoints and subsequent GRPO models for studying token-level behavior during the transition from SFT to RL. • 14 items • Updated 3 days ago

updated a model 3 days ago

zbeeb/Qwen2.5-3B-Base-GRPO

Text Generation • 3B • Updated 3 days ago • 16

published a model 3 days ago

zbeeb/Qwen2.5-3B-Base-GRPO

Text Generation • 3B • Updated 3 days ago • 16

updated a collection 6 days ago

OpenR1 SFT to GRPO: Token-Level Study

Collection

Matched OpenR1 SFT checkpoints and subsequent GRPO models for studying token-level behavior during the transition from SFT to RL. • 14 items • Updated 3 days ago

published a dataset 6 days ago

zbeeb/openr1-token-level-training-logs-20261007

Preview • Updated 6 days ago • 1.6k

updated a dataset 6 days ago

zbeeb/openr1-token-level-training-logs-20261007

Preview • Updated 6 days ago • 1.6k

updated a collection 7 days ago

OpenR1 SFT to GRPO: Token-Level Study

Collection

Matched OpenR1 SFT checkpoints and subsequent GRPO models for studying token-level behavior during the transition from SFT to RL. • 14 items • Updated 3 days ago

updated a model 7 days ago

zbeeb/Qwen2.5-1.5B-Base-GRPO

Text Generation • 2B • Updated 7 days ago • 422

published a model 7 days ago

zbeeb/Qwen2.5-1.5B-Base-GRPO

Text Generation • 2B • Updated 7 days ago • 422

updated a collection 7 days ago

OpenR1 SFT to GRPO: Token-Level Study

Collection

Matched OpenR1 SFT checkpoints and subsequent GRPO models for studying token-level behavior during the transition from SFT to RL. • 14 items • Updated 3 days ago

updated a model 7 days ago

zbeeb/Qwen2.5-Math-1.5B-Base-GRPO

Text Generation • 2B • Updated 7 days ago • 442 • 1

published a model 7 days ago

zbeeb/Qwen2.5-Math-1.5B-Base-GRPO

Text Generation • 2B • Updated 7 days ago • 442 • 1

updated a collection 7 days ago

OpenR1 SFT to GRPO: Token-Level Study

Collection

Matched OpenR1 SFT checkpoints and subsequent GRPO models for studying token-level behavior during the transition from SFT to RL. • 14 items • Updated 3 days ago