Zhaolin Gao's picture

2 5 6

Zhaolin Gao

GitBag

·

https://zhaolingao.github.io/

AI & ML interests

Reinforcement Learning from Human Feedback

Recent Activity

updated a dataset 28 days ago

GitBag/math_qwen3_1.7B_8192_n_128_eval_len

published a dataset 28 days ago

GitBag/math_qwen3_1.7B_8192_n_128_eval_len

updated a dataset 28 days ago

GitBag/math_qwen2.5_3B_8192_n_128_eval_len

View all activity

Organizations

GitBag 's models 328

GitBag/rebel_ultrafeedback_armo_OneBatch_newprob_full_lr_1e-6_eta_1e4_bs_128_1722279786

Text Generation • 8B • Updated Jul 30, 2024 • 5

GitBag/rebel_ultrafeedback_armo_OneBatch_newprob_full_lr_1e-6_eta_1e3_bs_128_1722275374

Text Generation • 8B • Updated Jul 29, 2024 • 5

GitBag/rebel_multiturn_chat_pairx_continue_1400_batch_size_32_kl_0_lr_3e-7_1722191156

Updated Jul 29, 2024

GitBag/simpo_ultrafeedback_armo_OneBatch_newprob_full_lr_1e-6_beta_10_gb_0.3_bs_128_1722052465

Text Generation • 8B • Updated Jul 27, 2024 • 5

GitBag/dpo_ultrafeedback_armo_OneBatch_newprob_full_lr_3e-7_beta_0.01_bs_128_1722056874

Text Generation • 8B • Updated Jul 27, 2024 • 5

GitBag/rebel_multiturn_chat_pairx_continue_1000_batch_size_32_kl_0_lr_3e-7_1722030780

Updated Jul 27, 2024

GitBag/rebel_ultrafeedback_armo_OneBatch_newprob_full_lr_5e-7_eta_1_bs_64_1721891508

Text Generation • 8B • Updated Jul 26, 2024 • 7

GitBag/rebel_ultrafeedback_armo_OneBatch_newprob_full_lr_1e-6_eta_10_bs_128_1721872264

Text Generation • 8B • Updated Jul 26, 2024 • 5

GitBag/rebel_multiturn_chat_hybrid_gen_pairx_wm_0.1_batch_size_32_kl_0_lr_3e-7_1721860439

Updated Jul 26, 2024

GitBag/rebel_multiturn_chat_hybrid_pairx_wm_0.1_eta_0.3_batch_size_32_kl_0_lr_3e-7_1721862031

Updated Jul 25, 2024

GitBag/rebel_multiturn_chat_hybrid_pairx_wm_0.1_eta_0.1_batch_size_32_kl_0_lr_3e-7_1721862112

Updated Jul 25, 2024

GitBag/rebel_multiturn_chat_hybrid_gen_pairx_batch_size_32_kl_0_lr_3e-7_1721671331

Updated Jul 24, 2024

GitBag/rebel_multiturn_chat_hybrid_pairx_batch_size_32_kl_0_lr_3e-7_1721674422

Updated Jul 24, 2024

GitBag/rebel_multiturn_chat_hybrid_gen_p_1_pairx_batch_size_32_kl_0_lr_3e-7_1721670552

Updated Jul 24, 2024

GitBag/rebel_ultrafeedback_armo_OneBatch_eta_50_lr_3e-7_1721675375

Updated Jul 22, 2024

GitBag/rebel_ultrafeedback_armo_eta_100_k_0_1721335956

Updated Jul 21, 2024

GitBag/rebel_multiturn-chat-last-turn-1-5_1721363579

Updated Jul 19, 2024

GitBag/rebel_multiturn-chat-turn-1-5_1721363058

Updated Jul 19, 2024

GitBag/rebel_multiturn-hh-turn-1-5_512_1721329638

Updated Jul 19, 2024

GitBag/rebel_multiturn-chat-last-turn-1-5_1721212244

Updated Jul 18, 2024

GitBag/rebel_multiturn-chat-turn-1-5_1721038007

Updated Jul 16, 2024

GitBag/rebel_multiturn-hh-turn-1-5_512_1720719737

Updated Jul 12, 2024

GitBag/rebel_multiturn-hh-turn-1-5_512_1720565116

Updated Jul 12, 2024

GitBag/rebel_multiturn-hh-turn-1-5_hybrid_1400_512_1720478927

Updated Jul 9, 2024

GitBag/rebel_ultrafeedback_armo_eta_100_1720462508

Updated Jul 9, 2024

GitBag/rebel_multiturn-hh-turn-1-5_hybrid_512_1720384473

Updated Jul 8, 2024

GitBag/rebel_ultrafeedback_armo_eta_3_1719971903

Updated Jul 5, 2024

GitBag/rebel_ultrafeedback_armo_1719876174

Updated Jul 5, 2024

GitBag/rebel_multiturn-hh-turn-1-5_hybrid_512_1719943074

Updated Jul 5, 2024

GitBag/rebel_multiturn-hh-turn-1-5_last_512_1719873017

Updated Jul 2, 2024