EM-RAFT

community

AI & ML interests

None defined yet.

Recent Activity

FlippyDora authored a paper 25 days ago

Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Models

FlippyDora authored a paper about 2 months ago

MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning

FlippyDora updated a model 2 months ago

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step146

View all activity

ScaleML-RLHF 's models 249

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step146

2B • Updated May 12

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step140

2B • Updated May 12

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step130

2B • Updated May 12

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step120

2B • Updated May 12 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step110

2B • Updated May 12 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step100

2B • Updated May 12

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step90

2B • Updated May 12 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step80

2B • Updated May 12 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step70

2B • Updated May 12 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step60

2B • Updated May 12 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step50

2B • Updated May 12 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step40

2B • Updated May 12 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step30

2B • Updated May 12 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step95-ckpt

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step20

2B • Updated May 12 • 1

ScaleML-RLHF/Qwen2.5-Math-1.5B-raftpp-numina_math_15_all-GVMonce-n8-8-step10

2B • Updated May 12 • 1

ScaleML-RLHF/Qwen2.5-Math1.5B-gvm-raftpp-iter6

2B • Updated May 7 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raft-plusplus-numina_math_em-cliphigher0.35-n8-8-iter1

8B • Updated Apr 25 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raftpp-cliphigher-n8-step130

8B • Updated Apr 24 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raftpp-cliphigher-n8-step120

8B • Updated Apr 24 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raftpp-cliphigher-n8-step110

8B • Updated Apr 24 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raftpp-cliphigher-n8-step100

8B • Updated Apr 24 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raftpp-cliphigher-n8-step90

8B • Updated Apr 24 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raftpp-cliphigher-n8-step80

8B • Updated Apr 23 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raftpp-cliphigher-n8-step70

8B • Updated Apr 23 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raftpp-cliphigher-n8-step60

8B • Updated Apr 23 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raftpp-cliphigher-n8-step50

8B • Updated Apr 23 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raftpp-cliphigher-n8-step40

8B • Updated Apr 23 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raftpp-cliphigher-n8-step30

8B • Updated Apr 23 • 1

ScaleML-RLHF/Qwen2.5-Math-7B-raftpp-cliphigher-n8-step20

8B • Updated Apr 23 • 1