Windy/Qwen_RM_80k_ratio50
Viewer
•
Updated
•
84.1k
•
28
W
Windy
AI & ML interests
None yet
Organizations
None yet
Windy/Qwen_RM_80k_nothinkspt_ratio50
Viewer
•
Updated
•
84.1k
•
28
Windy/Qwen_RM_80k_ratio90
Viewer
•
Updated
•
158k
•
27
Windy/Qwen_RM_80k_ratio99
Viewer
•
Updated
•
143k
•
26
Windy/Qwen_RM_80k_ratio95
Viewer
•
Updated
•
149k
•
31
Windy/Qwen_RM_80k_ratio100
Viewer
•
Updated
•
142k
•
29
Windy/Qwen_RM_80k_ratio80
Viewer
•
Updated
•
177k
•
31
Windy/Qwen_RM_80k
Viewer
•
Updated
•
84.1k
•
27
Windy/FLAN_500
Viewer
•
Updated
•
27.2k
•
28
Windy/FLAN_3k
Viewer
•
Updated
•
83k
•
27
Windy/FLAN
Viewer
•
Updated
•
25.8k
•
34
Windy/SynPO-Seed_Data
Viewer
•
Updated
•
18.2k
•
29
Windy/MetaMathQA_short
Viewer
•
Updated
•
395k
•
31
Windy/MetaMathQA_with_rejections-gpt2m
Viewer
•
Updated
•
155k
•
26
•
1
Windy/mistralbase_bsln_sppo_t4_10k
Viewer
•
Updated
•
10k
•
30
Windy/llama3base_bsln_sppo_t4_10k
Viewer
•
Updated
•
10k
•
24
Windy/llama3base_bsln_sppo_t3_10k
Viewer
•
Updated
•
10k
•
26
•
1
Windy/mistralbase_bsln_sppo_t3_10k
Viewer
•
Updated
•
10k
•
30
Windy/mistralbase_bsln_sppo_t2_10k
Viewer
•
Updated
•
10k
•
30
Windy/llama3base_bsln_sppo_t2_10k
Viewer
•
Updated
•
10k
•
27
Windy/llama3base_bsln_sppo_t1_10k
Viewer
•
Updated
•
10k
•
29
Windy/mistralbase_bsln_sppo_t1_10k
Viewer
•
Updated
•
10k
•
29
Windy/mistralbase_bsln_sppo_t0_10k
Viewer
•
Updated
•
10k
•
30
Windy/llama3base_bsln_sppo_t0_10k
Viewer
•
Updated
•
10k
•
30
Windy/llama3base_best_worst_finalablation_synpo_50k
Viewer
•
Updated
•
50k
•
27
Windy/llama3base_best_worst_finalablation_synpo_20k
Viewer
•
Updated
•
20k
•
25
Windy/llama3base_best_worst_finalablation_ultra_50k
Viewer
•
Updated
•
50k
•
30
Windy/llama3base_best_worst_finalablation_ultra_20k
Viewer
•
Updated
•
20k
•
32
Windy/llama3base_rewriter_finalablation_synpo_50k
Viewer
•
Updated
•
50k
•
32
Windy/llama3base_best_worst_finalablation_selfins_20k
Viewer
•
Updated
•
20k
•
25