Permissive Post-Training

permissive-post-train's activity

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

cabbage972 

updated a collection 2 days ago

Phase 2: reasoning SFT

Collection

Reasoning SFT on 30K samples of OpenThoughts3 (OT30K) or another reasoning dataset, and the checkpoints each run starts from. • 104 items • Updated 2 days ago

cabbage972 

updated a dataset 2 days ago

permissive-post-train/evaluation-records

Updated 2 days ago • 330

cabbage972 

updated a collection 8 days ago

Phase 2: reasoning SFT

Collection

Reasoning SFT on 30K samples of OpenThoughts3 (OT30K) or another reasoning dataset, and the checkpoints each run starts from. • 104 items • Updated 2 days ago