·
AI & ML interests
LLM Post-Training
Organizations
None yet
Renjie-Ranger/no-critique-big_math_summary_C-plus_no_concise_default_bsz_512_rollout_8-global_step_20
8B • Updated
• 4
Renjie-Ranger/v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_default_bsz_512-global_step_10
8B • Updated
• 3
Renjie-Ranger/no-critique-big_math_summary_C-plus_no_concise_default_bsz_512_rollout_8-global_step_10
8B • Updated
• 5
Renjie-Ranger/critique_slash_math_good_bad_slash_test_no_extra_space_slash_Qwen25-7B
8B • Updated
• 5
Renjie-Ranger/nano-critique-big_math_summary_C-plus_no_concise_default_Cplus_diversity-global_step_80
8B • Updated
• 4
Renjie-Ranger/nano-critique-big_math_summary_C-plus_no_concise_default_Cplus_diversity-global_step_60
8B • Updated
• 4
Renjie-Ranger/nano-critique-big_math_summary_C-plus_no_concise_default_Cplus_diversity-global_step_50
8B • Updated
• 3
Renjie-Ranger/nano-critique-big_math_summary_C-plus_no_concise_default_Cplus_diversity-global_step_40
8B • Updated
• 3
Renjie-Ranger/nano-critique-big_math_summary_C-plus_no_concise_default_Cplus_diversity-global_step_30
8B • Updated
• 4
Renjie-Ranger/nano-critique-big_math_summary_C-plus_no_concise_default_Cplus_diversity-global_step_10
8B • Updated
• 4
Renjie-Ranger/CCFT-v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_default_Cplus_d-global_step_10
Updated
Renjie-Ranger/CCFT-v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_default_loss_sum-global_step_90
8B • Updated
• 4
Renjie-Ranger/CCFT-v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_default_loss_sum-global_step_80
8B • Updated
• 3
Renjie-Ranger/CCFT-v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_default_loss_sum-global_step_60
8B • Updated
• 4
Renjie-Ranger/CCFT-v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_default_loss_sum-global_step_50
8B • Updated
• 3
Renjie-Ranger/CCFT-v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_default_loss_sum-global_step_40
8B • Updated
• 2
Renjie-Ranger/CCFT-v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_default_loss_sum-global_step_30
8B • Updated
• 4
Renjie-Ranger/CCFT-v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_default_loss_sum-global_step_20
8B • Updated
• 2
Renjie-Ranger/CCFT-v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_default_loss_sum-global_step_10
8B • Updated
• 3
Renjie-Ranger/critique_slash_math_good_bad_slash_test_user_feedback_slash_Qwen25-7B
8B • Updated
• 4
Renjie-Ranger/CCFT-v1-GPT5nano-critique-simple_rl_train_no_concise-global_step_5
8B • Updated
• 4
Renjie-Ranger/CCFT-v1-GPT5nano-critique-simple_rl_train_no_concise-global_step_40
8B • Updated
• 3
Renjie-Ranger/CCFT-v1-GPT5nano-critique-simple_rl_train_no_concise-global_step_35
8B • Updated
• 2
Renjie-Ranger/CCFT-v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_partial_online-global_step_75
8B • Updated
• 3
Renjie-Ranger/CCFT-v1-GPT5nano-critique-simple_rl_train_no_concise-global_step_30
8B • Updated
• 3
Renjie-Ranger/CCFT-v1-GPT5nano-critique-simple_rl_train_no_concise-global_step_25
8B • Updated
• 3
Renjie-Ranger/CCFT-v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_partial_online-global_step_70
8B • Updated
• 2
Renjie-Ranger/CCFT-v1-GPT5nano-critique-simple_rl_train_no_concise-global_step_20
8B • Updated
• 3
Renjie-Ranger/CCFT-v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_partial_online-global_step_65
8B • Updated
• 3
Renjie-Ranger/CCFT-v1-GPT5nano-critique-simple_rl_train_no_concise-global_step_15
8B • Updated
• 4