joyfine/router_SFT_larger_model_generated_data_Math_Qwen3-4B Viewer • Updated Apr 1 • 2.26k • 155 • 1
joyfine/router_SFT_self_generated_data_mmlu_pro_science_Qwen3-14B Viewer • Updated Mar 31 • 3.27k • 4
joyfine/router_SFT_self_generated_data_mmlu_pro_science_Qwen3-1.7B Viewer • Updated Mar 31 • 3.27k • 8
joyfine/router_SFT_self_generated_data_mmlu_pro_science_Qwen3-0.6B Viewer • Updated Mar 31 • 3.27k • 7
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_Qwen3-14B Viewer • Updated Mar 3 • 3.27k • 8
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_Qwen3-8B Viewer • Updated Mar 3 • 3.27k • 10
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_Qwen3-4B Viewer • Updated Mar 3 • 3.27k • 10
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_Qwen3-1.7B Viewer • Updated Mar 3 • 3.27k • 7
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_Qwen3-0.6B Viewer • Updated Mar 3 • 3.27k • 8
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_Qwen3-14B_rollout Viewer • Updated Mar 3 • 171 • 8
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_Qwen3-8B_rollout Viewer • Updated Mar 3 • 302 • 7
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_Qwen3-4B_rollout Viewer • Updated Mar 3 • 111 • 12
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_Qwen3-1.7B_rollout Viewer • Updated Mar 3 • 1.78k • 12
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_Qwen3-0.6B_rollout Viewer • Updated Mar 3 • 2.76k • 7