felixZzz/4b_student_len16k_custom_12xepoch_samebs_1119 Text Generation • 4B • Updated 13 days ago • 45
felixZzz/np_4b_len16k_custom_teacher_custom_student_acc_rolloutY_principle_mix-1118 Text Generation • 4B • Updated 14 days ago • 43
felixZzz/np_4b_len16k_custom_teacher_custom_student_onlyratio_rolloutY_mix-0113 Text Generation • 4B • Updated 15 days ago • 65
felixZzz/np_4b_teacher_8b_student_len16k_custom_teacher_custom_student_acc_rolloutY_mix-0116 Text Generation • 8B • Updated 16 days ago • 46
felixZzz/np_4b_len16k_custom_teacher_custom_student_wrong_mix-0113 Text Generation • 4B • Updated 18 days ago • 43
felixZzz/np_4b_len16k_custom_teacher_custom_student_onlyacc_rolloutY_v2_mix-0113 Text Generation • 4B • Updated 19 days ago • 56
felixZzz/np_4b_len16k_custom_teacher_custom_student_random_mix-0113 Text Generation • 4B • Updated 19 days ago • 47
felixZzz/np_4b_len16k_custom_teacher_custom_student_acc_rolloutY_principle_mix Viewer • Updated 15 days ago • 33.4k • 34
felixZzz/np_4b_len16k_custom_teacher_custom_student_acc_rolloutY_principle Viewer • Updated 15 days ago • 16.7k • 17
felixZzz/np_4b_len16k_custom_teacher_response-3-custom_8b_student_logps Viewer • Updated 15 days ago • 16.7k • 16
felixZzz/np_4b_len16k_custom_teacher_response-6-custom_8b_student_logps Viewer • Updated 15 days ago • 16.7k • 17
felixZzz/np_4b_len16k_custom_teacher_response-7-custom_8b_student_logps Viewer • Updated 15 days ago • 16.7k • 15
felixZzz/np_4b_len16k_custom_teacher_response-5-custom_8b_student_logps Viewer • Updated 15 days ago • 16.7k • 17
felixZzz/np_4b_len16k_custom_teacher_response-4-custom_8b_student_logps Viewer • Updated 15 days ago • 16.7k • 18
felixZzz/np_4b_len16k_custom_teacher_response-2-custom_8b_student_logps Viewer • Updated 15 days ago • 16.7k • 15