Models
4,066
Warm
LegendaryDawn/SDRL-freq-Qwen3-4B-Base-majority_n8_l2048-GRPO_n8_bs256_long8-step200
0
·125
·Mar 2026

Warm
Kazuki1450/Qwen3-1.7B-Base_dsum_3_6_rel_1e-1_alt_oracle1_noisy9_1p0_0p0_1p0_grpo_42_rule
0
·124
·Mar 2026

Warm
Kazuki1450/Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_alt_1_per_10_1p0_0p0_1p0_grpo_42_rule
0
·121
·Mar 2026

