a3ilab-llm-uncertainty/gemma4_12B_zhtw_10240_lr1e-6_ep5_64_128_256_turn_v6_no_cot_methodA2_1_2_apigen_have_paraell Updated 1 day ago
a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_turn_v6_no_cot_methodA2_1_2_apigen_have_paraell Text Generation • Updated 1 day ago • 11
a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_turn_v6_no_cot_methodA2_1_2_apigen_have_paraell_40ver Updated 1 day ago
a3ilab-llm-uncertainty/gemma4_12B_zhtw_10240_lr1e-6_ep5_64_128_256_turn_v6_no_cot_methodA2_1_2_apigen_paraell_40ver Updated 3 days ago
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_2_1_2_llamafactory_oringal_train Text Generation • Updated 5 days ago • 13 • 1
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_simple_cot2_v6data_eng_multi-turn_only Text Generation • Updated 5 days ago • 28
a3ilab-llm-uncertainty/gemma4_12B_zhtw_10240_lr5e-7_ep5_64_128_256_turn_v6_no_cot_methodA2_1_2 Updated 5 days ago
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_2_1_2_llamafactory_oringal_train_upload_ver_40 Updated 5 days ago • 1
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_simple_cot_v6data_original1_upload_ver40 Updated 15 days ago
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256simple_cot_v6data_apigen_only1_upload_40 Updated 15 days ago
a3ilab-llm-uncertainty/xlam_multi_turn_FUNreason_the_original_3epoch_gradient_accumulate32 Updated Nov 12, 2025 • 11