xw1234gan/Extended_GRPO_KL_Qwen2.5-3B-Instruct_MATH_beta0.01_lr1e-05_mb2_ga128_n2048_seed42 Text Generation • 3B • Updated Apr 4 • 5
xw1234gan/Extended_Merging_Prob_Qwen2.5-3B-Instruct_MATH_lr1e-05_mb2_ga128_n2048_seed42 Text Generation • 3B • Updated Apr 1 • 8
xw1234gan/Extended_Merging_Qwen2.5-3B-Instruct_MATH_lr1e-05_mb2_ga128_n2048_seed42 Text Generation • 3B • Updated Mar 29 • 4