EM-RAFT

community

AI & ML interests

None defined yet.

Recent Activity

FlippyDora updated a model 8 days ago

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

FlippyDora published a model 8 days ago

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

FlippyDora updated a model 8 days ago

ScaleML-RLHF/Llama-1B-em-raftpp-iter10

View all activity

ScaleML-RLHF 's models 260

ScaleML-RLHF/qwmathbase_ppo_n1_step60

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_grpo_n4_bz512_step100

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_raw_raft_step300

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_non_neg_grpo_step60

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_ppo_n1_step200

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_ppo_n1_step120

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_ppo_n1_step140

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_raftpp_bz128_step200

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_raf_raft_n4_bz128_step20

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_raftpp_bz128_step20

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_grpo_n4_bz512_step60

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_non_neg_grpo_step160

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_raf_raft_n4_bz128_step100

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_ppo_n1_step20

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_weighted_sft_bz512_step140

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_full_raft_step60

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_full_raft_step20

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_raw_raft_step20

8B • Updated Mar 20 • 3

ScaleML-RLHF/qwmathbase_weighted_sft_bz512_step60

ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_flat_em_stage1n64-sample8-iter