Windy/Qwen_RM_80k_ratio50
Viewer • Updated • 84.1k • 22
W
Windy
AI & ML interests
None yet
Organizations
None yet
Windy/Qwen_RM_80k_nothinkspt_ratio50
Viewer • Updated • 84.1k • 10
Windy/Qwen_RM_80k_ratio90
Viewer • Updated • 158k • 32
Windy/Qwen_RM_80k_ratio99
Viewer • Updated • 143k • 25
Windy/Qwen_RM_80k_ratio95
Viewer • Updated • 149k • 19
Windy/Qwen_RM_80k_ratio100
Viewer • Updated • 142k • 20
Windy/Qwen_RM_80k_ratio80
Viewer • Updated • 177k • 14
Windy/Qwen_RM_80k
Viewer • Updated • 84.1k • 23
Windy/FLAN_500
Viewer • Updated • 27.2k • 45
Windy/FLAN_3k
Viewer • Updated • 83k • 42
Windy/FLAN
Viewer • Updated • 25.8k • 5
Windy/SynPO-Seed_Data
Viewer • Updated • 18.2k • 21
Windy/MetaMathQA_short
Viewer • Updated • 395k • 30
Windy/MetaMathQA_with_rejections-gpt2m
Viewer • Updated • 155k • 13 • 1
Windy/mistralbase_bsln_sppo_t4_10k
Viewer • Updated • 10k • 17
Windy/llama3base_bsln_sppo_t4_10k
Viewer • Updated • 10k • 8
Windy/llama3base_bsln_sppo_t3_10k
Viewer • Updated • 10k • 9 • 1
Windy/mistralbase_bsln_sppo_t3_10k
Viewer • Updated • 10k • 31
Windy/mistralbase_bsln_sppo_t2_10k
Viewer • Updated • 10k • 24
Windy/llama3base_bsln_sppo_t2_10k
Viewer • Updated • 10k • 16
Windy/llama3base_bsln_sppo_t1_10k
Viewer • Updated • 10k • 30
Windy/mistralbase_bsln_sppo_t1_10k
Viewer • Updated • 10k • 17
Windy/mistralbase_bsln_sppo_t0_10k
Viewer • Updated • 10k • 21
Windy/llama3base_bsln_sppo_t0_10k
Viewer • Updated • 10k • 24
Windy/llama3base_best_worst_finalablation_synpo_50k
Viewer • Updated • 50k • 90
Windy/llama3base_best_worst_finalablation_synpo_20k
Viewer • Updated • 20k • 16
Windy/llama3base_best_worst_finalablation_ultra_50k
Viewer • Updated • 50k • 16
Windy/llama3base_best_worst_finalablation_ultra_20k
Viewer • Updated • 20k • 11
Windy/llama3base_rewriter_finalablation_synpo_50k
Viewer • Updated • 50k • 15
Windy/llama3base_best_worst_finalablation_selfins_20k
Viewer • Updated • 20k • 19