Renjie's picture

2 17 2

Renjie

RogerLos

·

AI & ML interests

LLM

Recent Activity

upvoted a paper 12 days ago

GoRL: An Algorithm-Agnostic Framework for Online Reinforcement Learning with Generative Policies

updated a model 19 days ago

RogerLos/all_pairs_rft_Qwen25-7B

published a model 19 days ago

RogerLos/all_pairs_rft_Qwen25-7B

View all activity

Organizations

None yet

RogerLos 's models 495

RogerLos/GRPO-GPT5nano-critique-big_math_vanilla_partial_online_math-verify-global_step_35

8B • Updated 24 days ago • 12

RogerLos/GRPO-GPT5nano-critique-big_math_vanilla_partial_online_math-verify-global_step_30

8B • Updated 24 days ago • 14

RogerLos/GRPO-GPT5nano-critique-big_math_vanilla_partial_online_math-verify-global_step_25

8B • Updated 24 days ago • 13

RogerLos/GRPO-GPT5nano-critique-big_math_vanilla_partial_online_math-verify-global_step_20

8B • Updated 24 days ago • 12

RogerLos/GRPO-GPT5nano-critique-big_math_vanilla_partial_online_math-verify-global_step_15

8B • Updated 24 days ago • 14

RogerLos/GRPO-GPT5nano-critique-wildchat_online_256-global_step_90

8B • Updated 26 days ago • 15

RogerLos/GRPO-GPT5nano-critique-wildchat_online_256-global_step_80

8B • Updated 26 days ago • 14

RogerLos/GRPO-GPT5nano-critique-wildchat_online_256-global_step_70

8B • Updated 26 days ago • 10

RogerLos/GRPO-GPT5nano-critique-wildchat_online_256-global_step_60

8B • Updated 26 days ago • 11

RogerLos/GRPO-GPT5nano-critique-wildchat_online_256-global_step_50

8B • Updated 26 days ago • 13

RogerLos/GRPO-GPT5nano-critique-wildchat_online_256-global_step_40

8B • Updated 26 days ago • 12

RogerLos/GRPO-GPT5nano-critique-wildchat_online_256-global_step_30

8B • Updated 26 days ago • 12

RogerLos/GRPO-GPT5nano-critique-wildchat_online_256-global_step_20

8B • Updated 26 days ago • 12

RogerLos/GRPO-GPT5nano-critique-wildchat_online_256-global_step_120

8B • Updated 26 days ago • 12

RogerLos/GRPO-GPT5nano-critique-wildchat_online_256-global_step_110

8B • Updated 26 days ago • 15

RogerLos/GRPO-GPT5nano-critique-wildchat_online_256-global_step_100

8B • Updated 26 days ago • 17

RogerLos/GRPO-GPT5nano-critique-wildchat_online_256-global_step_10

8B • Updated 26 days ago • 18

RogerLos/CCFT-v1-GPT5nano-critique-wildchat_v1_pro_fully_positive-global_step_5

Updated 27 days ago

RogerLos/CCFT-v1-GPT5nano-critique-wildchat_v1_pro_fully_positive-global_step_40

8B • Updated 27 days ago • 11

RogerLos/CCFT-v1-GPT5nano-critique-wildchat_v1_pro_fully_positive-global_step_35

8B • Updated 27 days ago • 13

RogerLos/CCFT-v1-GPT5nano-critique-wildchat_v1_pro_fully_positive-global_step_30

8B • Updated 27 days ago • 12

RogerLos/CCFT-v1-GPT5nano-critique-wildchat_v1_pro_fully_positive-global_step_25

8B • Updated 27 days ago • 11

RogerLos/CCFT-v1-GPT5nano-critique-wildchat_v1_pro_fully_positive-global_step_20

8B • Updated 27 days ago • 12

RogerLos/CCFT-v1-GPT5nano-critique-wildchat_v1_pro_fully_positive-global_step_15

8B • Updated 27 days ago • 13

RogerLos/CCFT-v1-GPT5nano-critique-wildchat_v1_pro_fully_positive-global_step_10

8B • Updated 27 days ago • 14

RogerLos/v1-GPT5nano-critique-big_math_summary_bsz_256_one_C-plus_mis_seq_cleaned-global_step_95

4B • Updated 28 days ago • 10

RogerLos/v1-GPT5nano-critique-big_math_summary_bsz_256_one_C-plus_mis_seq_cleaned-global_step_90

4B • Updated 28 days ago • 15

RogerLos/v1-GPT5nano-critique-big_math_summary_bsz_256_one_C-plus_mis_seq_cleaned-global_step_85

4B • Updated 28 days ago • 12

RogerLos/v1-GPT5nano-critique-big_math_summary_bsz_256_one_C-plus_mis_seq_cleaned-global_step_80

4B • Updated 28 days ago • 15

RogerLos/v1-GPT5nano-critique-big_math_summary_bsz_256_one_C-plus_mis_seq_cleaned-global_step_75

4B • Updated 28 days ago • 13