EM-RAFT

community

AI & ML interests

None defined yet.

Recent Activity

FlippyDora authored a paper about 2 months ago

PRL: Process Reward Learning Improves LLMs' Reasoning Ability and Broadens the Reasoning Boundary

FlippyDora submitted a paper about 2 months ago

PRL: Process Reward Learning Improves LLMs' Reasoning Ability and Broadens the Reasoning Boundary

FlippyDora updated a model 7 months ago

ScaleML-RLHF/Llama-1B-em-raftpp-iter4

View all activity

ScaleML-RLHF 's models 260

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_140

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_130

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_120

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_110

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_100

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_90

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_80

2B • Updated Mar 22, 2025

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_70

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_60

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_50

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_40

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_30

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_20

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_15_all-n4-step_10

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-plusplus-numina_math_em-sample1n8-sample4-iter1-step_9

2B • Updated Mar 22, 2025 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-plusplus-numina_math_em-sample1n8-sample4-iter1-step_5

2B • Updated Mar 22, 2025

ScaleML-RLHF/verl-math-new-Qwen2.5-Math-1.5B-raft-plusplus-numina_math-n4

Updated Mar 21, 2025

ScaleML-RLHF/verl-math-new-Qwen2.5-1.5B-Instruct-raft-vanilla-numina_math_flat_em_stage1n64-sample64-iter1

Updated Mar 21, 2025

ScaleML-RLHF/verl-math-new-Qwen2.5-0.5B-Instruct-raft-vanilla-numina_math_flat_em_stage1n64-sample64-iter1

Updated Mar 21, 2025

ScaleML-RLHF/verl-math-new-Qwen2.5-0.5B-Instruct-raft-vanilla-numina_math-n4

Updated Mar 21, 2025

ScaleML-RLHF/qwmathbase_raftpp_bz128_step80

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_non_neg_grpo_step140

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raw_raft_step160

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raf_raft_n4_bz128_step180

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raw_raft_step200

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raw_raft_step220

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_grpo_n4_bz512_step80

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raftpp_bz128_step120

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_full_raft_step180

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raf_raft_n4_bz128_step60

8B • Updated Mar 20, 2025 • 1