Zbib M

zbeeb's activity

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

updated a collection about 18 hours 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 about 18 hours ago

updated a model about 18 hours ago

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

Text Generation • 3B • Updated about 18 hours ago

published a model about 18 hours ago

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

Text Generation • 3B • Updated about 18 hours ago

updated a collection about 18 hours 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 about 18 hours ago

updated a model about 18 hours ago

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

Text Generation • 3B • Updated about 18 hours ago

published a model about 18 hours ago

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

Text Generation • 3B • Updated about 18 hours ago

updated a collection 4 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 about 18 hours ago

published a dataset 4 days ago

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

Preview • Updated 4 days ago • 1.6k

updated a dataset 4 days ago

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

Preview • Updated 4 days ago • 1.6k

updated a collection 4 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 about 18 hours ago

updated a model 4 days ago

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

Text Generation • 2B • Updated 4 days ago • 393

published a model 4 days ago

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

Text Generation • 2B • Updated 4 days ago • 393

updated a collection 4 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 about 18 hours ago

updated a model 4 days ago

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

Text Generation • 2B • Updated 4 days ago • 392 • 1

published a model 4 days ago

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

Text Generation • 2B • Updated 4 days ago • 392 • 1

updated a collection 4 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 about 18 hours ago

updated a model 4 days ago

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

Text Generation • 3B • Updated 4 days ago • 391

published a model 4 days ago

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

Text Generation • 3B • Updated 4 days ago • 391

upvoted a paper 5 days ago

Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation

Paper • 2610.05076 • Published 7 days ago • 26

updated a collection 5 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 about 18 hours ago