SkillFactory: Self-Distillation For Learning Cognitive Behaviors Paper • 2512.04072 • Published 8 days ago • 3
Zaynes/SFT-TrainingData-Example_Output_Repo_reflections5_formats-C_full Viewer • Updated 8 days ago • 14.7k • 6
Zaynes/SFT-TrainingData-Example_Output_Repo_reflections5_formats-C_full Viewer • Updated 8 days ago • 14.7k • 6
Other Datasets Collection Canonical prompt datasets were used for generating data for SFT and for performing RL (as well as evals). • 4 items • Updated 8 days ago
SkillFactory/BF_EVAL-cd3args-Qwen2.5-1.5B-Instruct-SkillFactory-RL Viewer • Updated 8 days ago • 49.9k • 10
SkillFactory/BF_EVAL-cd3args-Qwen2.5-1.5B-Instruct-SkillFactory-RL Viewer • Updated 8 days ago • 49.9k • 10
SkillFactory/SFT_DATA-openthoughts-1k_rows-main-Qwen2.5-7B-Instruct-SkillFactory Viewer • Updated 8 days ago • 1k • 10
SkillFactory/SFT_DATA-openthoughts-1k_rows-main-Qwen2.5-7B-Instruct-SkillFactory Viewer • Updated 8 days ago • 1k • 10
SkillFactory/SFT_DATA-openthoughts-10k_rows-main-Qwen2.5-7B-Instruct-SkillFactory Viewer • Updated 8 days ago • 10k • 6