Renjie's picture

2 18 2

Renjie

RogerLos

·

AI & ML interests

LLM

Recent Activity

upvoted a paper 9 days ago

Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics

upvoted a paper 22 days ago

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

updated a model 29 days ago

RogerLos/all_pairs_rft_Qwen25-7B

View all activity

Organizations

None yet

RogerLos 's models 495

RogerLos/GRPO_C-plus_all_bsz_256_1k_C-plus_mis_seq_rft_rerun-global_step_30

4B • Updated Nov 13 • 4

RogerLos/GRPO_C-plus_all_bsz_256_1k_C-plus_mis_seq_rft_rerun-global_step_25

4B • Updated Nov 13 • 3

RogerLos/GRPO_C-plus_all_bsz_256_1k_C-plus_mis_seq_rft_rerun-global_step_130

4B • Updated Nov 13 • 3

RogerLos/GRPO_C-plus_all_bsz_256_1k_C-plus_mis_seq_rft_rerun-global_step_125

4B • Updated Nov 13 • 4

RogerLos/GRPO_C-plus_all_bsz_256_1k_C-plus_mis_seq_rft_rerun-global_step_120

4B • Updated Nov 13 • 3

RogerLos/GRPO_C-plus_all_bsz_256_1k_C-plus_mis_seq_rft_rerun-global_step_115

4B • Updated Nov 13 • 3

RogerLos/GRPO_C-plus_all_bsz_256_1k_C-plus_mis_seq_rft_rerun-global_step_110

4B • Updated Nov 13 • 3

RogerLos/GRPO_C-plus_all_bsz_256_1k_C-plus_mis_seq_rft_rerun-global_step_105

4B • Updated Nov 13 • 4

RogerLos/GRPO_C-plus_all_bsz_256_1k_C-plus_mis_seq_rft_rerun-global_step_100

4B • Updated Nov 13 • 4

RogerLos/curriculum_16k_long-cot_Qwen2.5-0.5B-Instruct

Updated Nov 11 • 4

RogerLos/curriculum_32k_long-cot_Qwen2.5-0.5B-Instruct

RogerLos/verl-grpo-original-Qwen2.5-7B-Instruct-global_step_90

8B • Updated Nov 11 • 3

RogerLos/verl-grpo-original-Qwen2.5-7B-Instruct-global_step_80

8B • Updated Nov 10 • 2

RogerLos/verl-grpo-original-Qwen2.5-7B-Instruct-global_step_70

8B • Updated Nov 10 • 4

RogerLos/verl-grpo-original-Qwen2.5-7B-Instruct-global_step_60

8B • Updated Nov 10 • 3

RogerLos/verl-grpo-original-Qwen2.5-7B-Instruct-global_step_50

8B • Updated Nov 10 • 4

RogerLos/verl-grpo-original-Qwen2.5-7B-Instruct-global_step_40

8B • Updated Nov 10 • 4

RogerLos/verl-grpo-original-Qwen2.5-7B-Instruct-global_step_30

8B • Updated Nov 10 • 2

RogerLos/verl-grpo-original-Qwen2.5-7B-Instruct-global_step_20

8B • Updated Nov 10 • 4

RogerLos/verl-grpo-original-Qwen2.5-7B-Instruct-global_step_110

8B • Updated Nov 10 • 4

RogerLos/verl-grpo-original-Qwen2.5-7B-Instruct-global_step_100

8B • Updated Nov 10 • 3

RogerLos/verl-grpo-original-Qwen2.5-7B-Instruct-global_step_10

8B • Updated Nov 10 • 4

RogerLos/verl-grpo-original-Qwen2.5-3B-Instruct-global_step_90

3B • Updated Nov 10 • 3

RogerLos/verl-grpo-original-Qwen2.5-3B-Instruct-global_step_80

3B • Updated Nov 10 • 4

RogerLos/verl-grpo-original-Qwen2.5-3B-Instruct-global_step_70

3B • Updated Nov 10 • 4

RogerLos/verl-grpo-original-Qwen2.5-3B-Instruct-global_step_60

3B • Updated Nov 10 • 3

RogerLos/verl-grpo-original-Qwen2.5-3B-Instruct-global_step_50

3B • Updated Nov 10 • 3

RogerLos/verl-grpo-original-Qwen2.5-3B-Instruct-global_step_40

3B • Updated Nov 10 • 3

RogerLos/verl-grpo-original-Qwen2.5-3B-Instruct-global_step_30

3B • Updated Nov 10 • 4

RogerLos/verl-grpo-original-Qwen2.5-3B-Instruct-global_step_20

3B • Updated Nov 10 • 4