violetxi/single-turn-eval-int_qwen3-4b_distill_teacher_reverse_kl_lr1e-7-n32 Viewer • Updated 3 days ago • 566 • 28
violetxi/single-turn-eval-int_qwen3-4b_distill_teacher_reverse_kl_lr1e-7-n32 Viewer • Updated 3 days ago • 566 • 28
violetxi/single-turn-eval-meta_feedback_qwen3-4b_step2_gpt-5-nano_gepa-n32 Viewer • Updated 13 days ago • 1.01k • 30
violetxi/single-turn-eval-meta_feedback_qwen3-4b_step2_gpt-5-nano_gepa-n32 Viewer • Updated 13 days ago • 1.01k • 30
violetxi/single-turn-eval-stage1_proof_pr_delta_variants-n32 Viewer • Updated 13 days ago • 1.01k • 23
violetxi/single-turn-eval-stage1_proof_pr_delta_variants-n32 Viewer • Updated 13 days ago • 1.01k • 23
violetxi/single-turn-eval-meta_feedback_qwen3-4b_step2_gpt-5.4_gepa-n32 Viewer • Updated 13 days ago • 1.01k • 24
violetxi/single-turn-eval-meta_feedback_qwen3-4b_step2_gpt-5.4_gepa-n32 Viewer • Updated 13 days ago • 1.01k • 24
violetxi/stage1_proof-qwen3-4b-grpo-imoproofbench-summary-reasoning-graded Viewer • Updated 17 days ago • 960 • 26