Permissive Post-Training

permissive-post-train's activity

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

cabbage972 

updated a dataset 3 days ago

permissive-post-train/evaluation-records

Updated 3 days ago • 216

cabbage972 

updated a collection 4 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. • 96 items • Updated 4 days ago