xw1234gan/cnk12_GRPO_KL_Qwen2.5-7B-Instruct_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL
Text Generation • 8B • Updated • 24
xingweigan
xw1234gan
AI & ML interests
None yet
Recent Activity
updated a model 6 days ago
xw1234gan/cnk12_GRPO_KL_Qwen2.5-7B-Instruct_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL published a model 6 days ago
xw1234gan/cnk12_GRPO_KL_Qwen2.5-7B-Instruct_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL updated a model 7 days ago
xw1234gan/cnk12_GRPO_KL_Qwen2.5-3B-Instruct_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKLOrganizations
None yet
xw1234gan/cnk12_GRPO_KL_Qwen2.5-3B-Instruct_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL
Text Generation • 3B • Updated • 18
xw1234gan/cnk12_GRPO_KL_Qwen2.5-1.5B-Instruct_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL
Text Generation • 2B • Updated • 25
xw1234gan/GRPO_KL_Qwen2.5-7B-Instruct_MATH_beta0_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN_NoKL
Text Generation • 8B • Updated • 26
xw1234gan/Extended_GRPO_KL_Qwen2.5-3B-Instruct_MATH_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL
Text Generation • 3B • Updated • 26
xw1234gan/Extended_GRPO_KL_Qwen2.5-1.5B-Instruct_MATH_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL
Text Generation • 2B • Updated • 29
xw1234gan/Merging_Qwen2.5-7B-Instruct_MMLU_lr1e-05_mb2_ga128_n2048_seed42
Text Generation • 8B • Updated • 27
xw1234gan/Fixed_Merging_Qwen2.5-7B-Instruct_MMLU_lr1e-05_mb2_ga128_n2048_seed42
Text Generation • 8B • Updated • 8
xw1234gan/GRPO_KL_Qwen2.5-7B-Instruct_MMLU_beta0.01_lr1e-05_mb2_ga128_n2048_seed42
Text Generation • 8B • Updated • 6
xw1234gan/Main_fixed_MATH_1_5B_step_10
Text Generation • 2B • Updated • 9
xw1234gan/Main_fixed_MATH_1_5B_step_9
Text Generation • 2B • Updated • 7
xw1234gan/Main_fixed_MATH_1_5B_step_8
Text Generation • 2B • Updated • 6
xw1234gan/Main_fixed_MATH_1_5B_step_7
Text Generation • 2B • Updated • 11
xw1234gan/Main_fixed_MATH_1_5B_step_6
Text Generation • 2B • Updated • 7
xw1234gan/Main_fixed_MATH_1_5B_step_5
Text Generation • 2B • Updated • 7
xw1234gan/Main_fixed_MATH_1_5B_step_4
Text Generation • 2B • Updated • 8
xw1234gan/Main_fixed_MATH_1_5B_step_3
Text Generation • 2B • Updated • 7
xw1234gan/Main_fixed_MATH_1_5B_step_2
Text Generation • 2B • Updated • 6
xw1234gan/Main_fixed_MATH_1_5B_step_1
Text Generation • 2B • Updated • 8
xw1234gan/cnk12_GRPO_KL_Qwen2.5-7B-Instruct_beta0.01_lr1e-05_mb2_ga128_n2048_seed42
Text Generation • 8B • Updated • 7
xw1234gan/olympiads_Adaptive_Merging_Qwen2.5-1.5B-Instruct_lr1e-05_mb2_ga128_n2048_seed42
Text Generation • 2B • Updated • 4
xw1234gan/olympiads_Main_1_5B_step_10
Text Generation • 2B • Updated • 4
xw1234gan/olympiads_Main_1_5B_step_9
Text Generation • 2B • Updated • 7
xw1234gan/olympiads_Main_1_5B_step_8
Text Generation • 2B • Updated • 5
xw1234gan/olympiads_Main_1_5B_step_7
Text Generation • 2B • Updated • 6
xw1234gan/olympiads_Main_1_5B_step_6
Text Generation • 2B • Updated • 5
xw1234gan/olympiads_Main_1_5B_step_5
Text Generation • 2B • Updated • 7
xw1234gan/olympiads_Main_1_5B_step_4
Text Generation • 2B • Updated • 7
xw1234gan/olympiads_Main_1_5B_step_3
Text Generation • 2B • Updated • 6
xw1234gan/olympiads_Main_1_5B_step_2
Text Generation • 2B • Updated • 5