a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_turn_v6_no_cot_aug_original_40ver
Text Generation • Updated • 12
LLM-Uncertainty
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_turn_v6_no_cot_aug_original
Text Generation • Updated • 11
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_simple_cot_v6data_only_answer_loss_aug_all_40ver
Text Generation • Updated • 14
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_simple_cot_v6data_only_answer_loss_aug_all
Text Generation • Updated • 15
a3ilab-llm-uncertainty/emma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_turn_v6_no_cot_aug_original_40ver
Updated
a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6ep5_64_128_256_v6_nocot_methodA2_1_2apigen_have_paraell500only_40
Updated
a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_turn_v6_no_cot_data_oringal_40ver
Text Generation • Updated • 15
a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_turn_v6_no_cot_data_oringal
Text Generation • Updated • 12
a3ilab-llm-uncertainty/gemma4_12B_6144_lr1e-6_ep5_64_128_256_turn_v6_no_cot_methodA2_1_2_llamafactory_oringal_train_40
Updated
a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_v6_data_oringal_llamafactory_oringal_train_ver40
Updated
a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_v6_methodA2_1_2_llamafactory_oringal_train
Text Generation • Updated • 17
a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_v6_data_oringal_llamafactory_oringal_train
Text Generation • Updated • 8
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_llamafactory_and_data_oringal_train_ver40
Updated
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_llamafactory_and_data_oringal_train
Text Generation • Updated • 23
a3ilab-llm-uncertainty/gemma4_12B_lr1e-6_ep5_64_128_256_turn_v6_no_cot_methodA2_1_2_llamafactory_oringal_train_40
Updated
a3ilab-llm-uncertainty/_ver40
Updated
a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_turn_v6_no_cot_methodA2_1_2apigen_have_paraell500only
Text Generation • Updated • 243
a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_turn_v6_nocot_A2_1_2_have_paraell20p_40ver
Updated
a3ilab-llm-uncertainty/gemma4_12B_zhtw_6144_lr1e-6_ep5_64_128_256_turn_v6_no_cot_methodA2_1_2_apigen_have_paraell20p
Text Generation • Updated • 5
a3ilab-llm-uncertainty/gemma4_12B_zhtw_10240_lr1e-6_ep5_64_128_256_turn_v6_no_cot_methodA2_1_2_apigen_have_paraell
Updated
a3ilab-llm-uncertainty/gemma4_12B_zhtw_10240_lr1e-6_ep5_64_128_256_turn_v6_no_cot_methodA2_1_2_apigen_paraell_40ver
Updated
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr1e-6_ep5_64_128_256_simple_cot_v6data_only_answer_loss_A_method2_1_2
Text Generation • Updated • 3
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr1e-6_ep5_64_128_256_simple_cot_v6data_only_answer_loss_apigen_only1
Text Generation • Updated • 5
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr1e-6_ep5_64_128_256_simple_cot_v6data_only_answer_loss_apigen_only1_40ver
Updated
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr1e-6_ep5_64_128_256_simple_cot_v6data_only_answer_loss_A_method2_1_2_40ver
Updated
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_simple_cot_v6data_original2_test_40ver
Updated
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_simple_cot_v6data_original2_test
Text Generation • Updated • 6
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 • 6
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
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_2_1_2_llamafactory_oringal_train
Text Generation • Updated • 7 • 1