AI & ML interests
None defined yet.
Recent Activity
View all activity
All of these models were trained on countdown 3args with Qwen2.5-1.5B-Instruct
-
SkillFactory/ablation-Qwen2.5-1.5B-Instruct-no_sample_order-SFT
2B • Updated • 3 -
SkillFactory/ablation-Qwen2.5-1.5B-Instruct-no_reflections-SFT
2B • Updated • 4 -
SkillFactory/ablation-Qwen2.5-1.5B-Instruct-no_prompt_diversity-SFT
2B • Updated • 3 -
SkillFactory/ablation-Qwen2.5-1.5B-Instruct-no_sample_order-RL
2B • Updated • 4
-
SkillFactory/openthoughts-Qwen2.5-7B-Instruct-QwQ-1k_rows-SFT
8B • Updated • 3 -
SkillFactory/openthoughts-Qwen2.5-7B-Instruct-QwQ-10k_rows-SFT
8B • Updated • 3 -
SkillFactory/openthoughts-Qwen2.5-7B-Instruct-SkillFactory-1k_rows-SFT
8B • Updated • 2 -
SkillFactory/openthoughts-Qwen2.5-7B-Instruct-SkillFactory-10k_rows-SFT
8B • Updated • 2
-
SkillFactory/EVAL-OT-Qwen2.5-7B-Instruct-RL
Viewer • Updated • 268 • 8 -
SkillFactory/EVAL_MATH500-OT-Qwen2.5-7B-Instruct-RL
Viewer • Updated • 500 • 6 -
SkillFactory/EVAL-OT-Qwen2.5-7B-Instruct-QwQ-1k_rows-RL
Viewer • Updated • 268 • 8 -
SkillFactory/EVAL_MATH500-OT-Qwen2.5-7B-Instruct-QwQ-1k_rows-RL
Viewer • Updated • 500 • 5
-
SkillFactory/SFT_DATA-cd3args-ablation-Qwen2.5-1.5B-Instruct-no_sample_order
Viewer • Updated • 14.7k • 8 -
SkillFactory/SFT_DATA-cd3args-ablation-Qwen2.5-1.5B-Instruct-no_reflections
Viewer • Updated • 14.7k • 8 -
SkillFactory/SFT_DATA-cd3args-ablation-Qwen2.5-1.5B-Instruct-no_prompt_diversity
Viewer • Updated • 3.01k • 9 -
SkillFactory/SFT_DATA-cd3args-baseline-Qwen2.5-1.5B-Instruct-STaR
Viewer • Updated • 14.7k • 8
Canonical prompt datasets were used for generating data for SFT and for performing RL (as well as evals).
-
SkillFactory/canonical_prompt_collection__more_evals
Viewer • Updated • 14.5k • 77 -
SkillFactory/canonical_prompt_collection
Viewer • Updated • 143k • 208 -
SkillFactory/RAW_DATA-openthoughts-Qwen2.5-7B-Instruct
Viewer • Updated • 1.25M • 196 -
SkillFactory/RAW_DATA-countdown3args-Qwen2.5-1.5B-Instruct
Viewer • Updated • 135k • 19
-
SkillFactory/EVAL-cd3args-Qwen2.5-1.5B-Instruct
Viewer • Updated • 11.5k • 9 -
SkillFactory/EVAL-cd3args-Qwen2.5-1.5B-Instruct-BoLT-SFT
Viewer • Updated • 11.5k • 8 -
SkillFactory/EVAL-cd3args-Qwen2.5-1.5B-Instruct-R1-SFT
Viewer • Updated • 11.5k • 11 -
SkillFactory/EVAL-cd3args-Qwen2.5-1.5B-Instruct-STaR-SFT
Viewer • Updated • 11.5k • 7
-
SkillFactory/SFT_DATA-cd3args-ablation-Qwen2.5-1.5B-Instruct-no_sample_order
Viewer • Updated • 14.7k • 8 -
SkillFactory/SFT_DATA-cd3args-ablation-Qwen2.5-1.5B-Instruct-no_reflections
Viewer • Updated • 14.7k • 8 -
SkillFactory/SFT_DATA-cd3args-ablation-Qwen2.5-1.5B-Instruct-no_prompt_diversity
Viewer • Updated • 3.01k • 9 -
SkillFactory/SFT_DATA-cd3args-baseline-Qwen2.5-1.5B-Instruct-STaR
Viewer • Updated • 14.7k • 8
All of these models were trained on countdown 3args with Qwen2.5-1.5B-Instruct
-
SkillFactory/ablation-Qwen2.5-1.5B-Instruct-no_sample_order-SFT
2B • Updated • 3 -
SkillFactory/ablation-Qwen2.5-1.5B-Instruct-no_reflections-SFT
2B • Updated • 4 -
SkillFactory/ablation-Qwen2.5-1.5B-Instruct-no_prompt_diversity-SFT
2B • Updated • 3 -
SkillFactory/ablation-Qwen2.5-1.5B-Instruct-no_sample_order-RL
2B • Updated • 4
Canonical prompt datasets were used for generating data for SFT and for performing RL (as well as evals).
-
SkillFactory/canonical_prompt_collection__more_evals
Viewer • Updated • 14.5k • 77 -
SkillFactory/canonical_prompt_collection
Viewer • Updated • 143k • 208 -
SkillFactory/RAW_DATA-openthoughts-Qwen2.5-7B-Instruct
Viewer • Updated • 1.25M • 196 -
SkillFactory/RAW_DATA-countdown3args-Qwen2.5-1.5B-Instruct
Viewer • Updated • 135k • 19
-
SkillFactory/openthoughts-Qwen2.5-7B-Instruct-QwQ-1k_rows-SFT
8B • Updated • 3 -
SkillFactory/openthoughts-Qwen2.5-7B-Instruct-QwQ-10k_rows-SFT
8B • Updated • 3 -
SkillFactory/openthoughts-Qwen2.5-7B-Instruct-SkillFactory-1k_rows-SFT
8B • Updated • 2 -
SkillFactory/openthoughts-Qwen2.5-7B-Instruct-SkillFactory-10k_rows-SFT
8B • Updated • 2
-
SkillFactory/EVAL-OT-Qwen2.5-7B-Instruct-RL
Viewer • Updated • 268 • 8 -
SkillFactory/EVAL_MATH500-OT-Qwen2.5-7B-Instruct-RL
Viewer • Updated • 500 • 6 -
SkillFactory/EVAL-OT-Qwen2.5-7B-Instruct-QwQ-1k_rows-RL
Viewer • Updated • 268 • 8 -
SkillFactory/EVAL_MATH500-OT-Qwen2.5-7B-Instruct-QwQ-1k_rows-RL
Viewer • Updated • 500 • 5
-
SkillFactory/EVAL-cd3args-Qwen2.5-1.5B-Instruct
Viewer • Updated • 11.5k • 9 -
SkillFactory/EVAL-cd3args-Qwen2.5-1.5B-Instruct-BoLT-SFT
Viewer • Updated • 11.5k • 8 -
SkillFactory/EVAL-cd3args-Qwen2.5-1.5B-Instruct-R1-SFT
Viewer • Updated • 11.5k • 11 -
SkillFactory/EVAL-cd3args-Qwen2.5-1.5B-Instruct-STaR-SFT
Viewer • Updated • 11.5k • 7