ccui46/q3_8b_offline_sft_tw_external_module_dead_end_early_stop_8750 Text Generation • 8B • Updated Jan 26 • 1
ccui46/q3_8b_offline_sft_tw_external_module_dead_end_early_stop_plain_thought_9250 Text Generation • 8B • Updated Jan 26 • 10
ccui46/q3_8b_offline_sft_tw_external_module_dead_end_early_stop_9000 Text Generation • 8B • Updated Jan 26 • 2
ccui46/q3_8b_offline_sft_tw_external_module_dead_end_early_stop_plain_thought_9500 Text Generation • 8B • Updated Jan 26 • 2
ccui46/q3_8b_offline_sft_tw_external_module_dead_end_early_stop_plain_thought_9750 Text Generation • 8B • Updated Jan 26 • 2
ccui46/q3_8b_offline_sft_tw_external_module_dead_end_early_stop_9250 Text Generation • 8B • Updated Jan 26 • 2
ccui46/q3_8b_offline_sft_tw_external_module_dead_end_early_stop_9500 Text Generation • 8B • Updated Jan 26 • 2
ccui46/q3_8b_offline_sft_tw_external_module_dead_end_early_stop_plain_thought_10000 Text Generation • 8B • Updated Jan 26 • 1
ccui46/q3_8b_offline_sft_tw_external_module_dead_end_early_stop_9750 Text Generation • 8B • Updated Jan 26 • 2
ccui46/q3_8b_offline_sft_tw_external_module_dead_end_early_stop_10000 Text Generation • 8B • Updated Jan 26 • 7
ccui46/q3_4b_offline_sft_aime_external_module_early_stop_plain_thought_250 Text Generation • 4B • Updated Jan 26 • 3
ccui46/q3_4b_offline_sft_aime_external_module_early_stop_plain_thought_500 Text Generation • 4B • Updated Jan 26 • 3
ccui46/q3_4b_offline_sft_aime_external_module_dead_end_early_stop_250 Text Generation • 4B • Updated Jan 26 • 3
ccui46/q3_4b_offline_sft_aime_external_module_early_stop_plain_thought_750 Text Generation • 4B • Updated Jan 26 • 3
ccui46/q3_4b_offline_sft_aime_external_module_dead_end_early_stop_500 Text Generation • 4B • Updated Jan 26 • 2
ccui46/q3_4b_offline_sft_aime_external_module_early_stop_plain_thought_1000 Text Generation • 4B • Updated Jan 26 • 3
ccui46/q3_4b_offline_sft_aime_external_module_early_stop_plain_thought_1250 Text Generation • 4B • Updated Jan 26 • 3
ccui46/q3_8b_offline_sft_tw_external_module_dead_end_early_stop_pos_filtered_plain_thought_500 Text Generation • 8B • Updated Jan 27 • 2