felixZzz/np_4b_len16k_custom_teacher_custom_student_acc_rolloutY_principle_mix Viewer • Updated Nov 18 • 33.4k • 7
felixZzz/np_4b_len16k_custom_teacher_custom_student_acc_rolloutY_principle Viewer • Updated Nov 18 • 16.7k • 6
felixZzz/np_4b_len16k_custom_teacher_response-3-custom_8b_student_logps Viewer • Updated Nov 17 • 16.7k • 8
felixZzz/np_4b_len16k_custom_teacher_response-6-custom_8b_student_logps Viewer • Updated Nov 17 • 16.7k • 13
felixZzz/np_4b_len16k_custom_teacher_response-7-custom_8b_student_logps Viewer • Updated Nov 17 • 16.7k • 15
felixZzz/np_4b_len16k_custom_teacher_response-5-custom_8b_student_logps Viewer • Updated Nov 17 • 16.7k • 8
felixZzz/np_4b_len16k_custom_teacher_response-4-custom_8b_student_logps Viewer • Updated Nov 17 • 16.7k • 7
felixZzz/np_4b_len16k_custom_teacher_response-2-custom_8b_student_logps Viewer • Updated Nov 17 • 16.7k • 7
felixZzz/np_4b_len16k_custom_teacher_response-1-custom_8b_student_logps Viewer • Updated Nov 17 • 16.7k • 7
felixZzz/np_4b_len16k_custom_teacher_response-0-custom_8b_student_logps Viewer • Updated Nov 17 • 16.7k • 8
felixZzz/np_4b_len16k_custom_teacher_custom_student_onlyratio_rolloutY_mix Viewer • Updated Nov 16 • 33.4k • 7
felixZzz/np_4b_len16k_custom_teacher_custom_student_onlyratio_rolloutY Viewer • Updated Nov 16 • 16.7k • 8
felixZzz/np_4b_len16k_custom_teacher_custom_student_onlyacc_rolloutY_v2_mix Viewer • Updated Nov 13 • 33.4k • 8
felixZzz/np_4b_len16k_custom_teacher_custom_student_onlyacc_rolloutY_v2 Viewer • Updated Nov 13 • 16.7k • 13
felixZzz/np_4b_len16k_custom_teacher_custom_student_onlyacc_rolloutY_mix Viewer • Updated Nov 12 • 33.4k • 8