·
AI & ML interests
None yet
Organizations
1231czx/REFUEL_sampled_h_from_sampled_len_ckp_2
Viewer
• Updated • 1 • 8
1231czx/REFUEL_sampled_h_from_sampled_len_ckp_1
Viewer
• Updated • 1 • 8
1231czx/REFUEL_sampled_h_from_sampled_len_ckp_0
Viewer
• Updated • 1 • 9
1231czx/REFUEL_5_turns_only
Viewer
• Updated • 1 • 9
1231czx/REFUEL_5_turns_only_ckp_4
Viewer
• Updated • 1 • 9
1231czx/REFUEL_5_turns_only_ckp_3
Viewer
• Updated • 1 • 9
1231czx/REFUEL_5_turns_only_ckp_2
Viewer
• Updated • 1 • 9
1231czx/REFUEL_5_turns_only_ckp_1
Preview
• Updated • 9
1231czx/REFUEL_5_turns_only_ckp_0
Viewer
• Updated • 1 • 9
1231czx/deepseek_gen_gsm8k_mistralprm_2
Viewer
• Updated • 719 • 8
1231czx/deepseek_gen_gsm8k_mistralprm_1
Viewer
• Updated • 600 • 9
1231czx/orm_mistraldatatrain_mistral_gsm8k_test
Viewer
• Updated • 1.32k • 8
1231czx/orm_mistraldatatrain_mistral_less_math_test
Viewer
• Updated • 500 • 8
1231czx/orm_mistraldatatrain_mistral_less_gsm8k_test
Viewer
• Updated • 1.32k • 9
1231czx/orm_mistraldatatrain_mistral_math_test
Viewer
• Updated • 500 • 8
1231czx/prm_2e6_bz32_1epoch_mistral_test_gsm8k
Viewer
• Updated • 1.32k • 10
1231czx/prm_2e6_bz32_1epoch_deepseek_test
Viewer
• Updated • 500 • 11
1231czx/real_prm_1e6_bz32_1epoch
Viewer
• Updated • 500 • 7
1231czx/prm_5e6_bz32_1epoch
Viewer
• Updated • 500 • 8
1231czx/prm_2e6_bz16_1epoch
Viewer
• Updated • 500 • 7
1231czx/prm_1e6_bz32_2epoch
Viewer
• Updated • 500 • 9
1231czx/prm_1e6_bz32_1epoch
Viewer
• Updated • 500 • 7
1231czx/hn_prm_conversation
Viewer
• Updated • 273k • 10
1231czx/rlhflow_mix_w_dart_math
Viewer
• Updated • 1.83M • 14
1231czx/rlhflow_mix_w_aimo_math
Viewer
• Updated • 2.17M • 14
1231czx/uf_chat_del_system
Viewer
• Updated • 208k • 10
1231czx/magpie_del_system
Viewer
• Updated • 550k • 11
1231czx/rlhflow_mixture_with_math_del_system
Viewer
• Updated • 2.76M • 11
Viewer
• Updated • 615k • 10
1231czx/rlhflow_mix_del_system_and_empty_round2
Viewer
• Updated • 1.24M • 11