cchoi1/humaneval_qwen7b_att_iter0_ppo_att50_sol10_explanations_dpo_1000 Viewer • Updated Apr 7, 2025 • 1.2k • 11
cchoi1/humaneval_qwen7b_att_iter0_ppo_att50_sol10_explanations Viewer • Updated Apr 7, 2025 • 3.38k • 13
cchoi1/humaneval_qwen7b_att_iter0_ppo_att50_sol50_incorrect_dpo_1000 Viewer • Updated Apr 7, 2025 • 1.2k • 15
cchoi1/humaneval_qwen32b_sol_best_of_200_relabeled_grpo_4000 Viewer • Updated Apr 6, 2025 • 4.8k • 16
cchoi1/humaneval_qwen32b_att_iter0_ppo_att20_sol10_explanations Viewer • Updated Apr 6, 2025 • 1.33k • 21
cchoi1/humaneval_qwen7b_att_iter0_ppo_att50_sol50_relabeled_grpo_1000 Viewer • Updated Apr 3, 2025 • 1.2k • 13
cchoi1/humaneval_qwen7b_att_iter0_ppo_att50_sol50_relabeled Viewer • Updated Apr 2, 2025 • 3.37k • 10
cchoi1/humaneval_qwen7b_att_iter0_ppo_att50_sol10_no_explanation Viewer • Updated Apr 2, 2025 • 3.35k • 7
cchoi1/humaneval_qwen32b_att_iter0_ppo_att20_sol10_v2_dpo_1000 Viewer • Updated Apr 2, 2025 • 1.2k • 14
cchoi1/humaneval_qwen7b_sol_iter0_ppo_att20_sol10_4_1_25_v2 Viewer • Updated Apr 2, 2025 • 1.45k • 12
cchoi1/humaneval_qwen7b_sol_iter0_ppo_att20_sol10_4_1_25_dpo_1000 Viewer • Updated Apr 2, 2025 • 1.2k • 19
cchoi1/humaneval_qwen7b_att_iter0_ppo_att50_sol50_relabeled_deduped_dpo_700 Viewer • Updated Apr 1, 2025 • 800 • 17
cchoi1/humaneval_qwen7b_att_iter0_ppo_att50_sol50_relabeled_deduped Viewer • Updated Apr 1, 2025 • 829 • 9
cchoi1/humaneval_qwen7b_att_iter0_ppo_att20_sol10_relabeled_deduped Viewer • Updated Apr 1, 2025 • 441 • 10