xw1234gan/cnk12_GRPO_KL_Qwen2.5-7B-Instruct_beta0.01_lr1e-05_mb2_ga128_n2048_seed42 Text Generation • 8B • Updated May 6 • 7
xw1234gan/olympiads_Adaptive_Merging_Qwen2.5-1.5B-Instruct_lr1e-05_mb2_ga128_n2048_seed42 Text Generation • 2B • Updated May 4 • 8
xw1234gan/olympiads_GRPO_KL_Qwen2.5-3B-Instruct_beta0.01_lr1e-05_mb2_ga128_n2048_seed42 Text Generation • 3B • Updated May 2 • 6