ScaleML-RLHF/Qwen2.5-Math-1.5B-raft-vanilla-numina_math_flat_em_stage1n64-sample8-iter
Updated
Edit Models filters
Showing models from
Tasks
Parameters
Inference Providers
Hardware
Models
260
Active filters: ScaleML-RLHF
ScaleML-RLHF/qwmathbase_raf_raft_n4_bz128_step180
8B • Updated • 11
ScaleML-RLHF/qwmathbase_ppo_n1_step120
8B • Updated • 11
ScaleML-RLHF/qwmathbase_grpo_n4_bz512_step60
8B • Updated • 11
ScaleML-RLHF/qwmathbase_raf_raft_n4_bz128_step80
8B • Updated • 11
ScaleML-RLHF/qwmathbase_weighted_sft_bz512_step140
8B • Updated • 10
ScaleML-RLHF/qwmathbase_raw_raft_step260
8B • Updated • 14
ScaleML-RLHF/qwmathbase_raftpp_bz128_step100
8B • Updated • 10
ScaleML-RLHF/qwmathbase_full_raft_step60
8B • Updated • 10
ScaleML-RLHF/qwmathbase_raf_raft_n4_bz128_step100
8B • Updated • 10
ScaleML-RLHF/qwmathbase_grpo_n4_bz512_step180
8B • Updated • 11
ScaleML-RLHF/qwmathbase_full_raft_step240
8B • Updated • 12
ScaleML-RLHF/qwmathbase_raw_raft_step220
8B • Updated • 11
ScaleML-RLHF/qwmathbase_grpo_n4_bz512_step80
8B • Updated • 11
ScaleML-RLHF/qwmathbase_ppo_n1_step200
8B • Updated • 10
ScaleML-RLHF/qwmathbase_weighted_sft_bz512_step200
8B • Updated • 10
ScaleML-RLHF/qwmathbase_raw_raft_step280
8B • Updated • 11
ScaleML-RLHF/qwmathbase_raf_raft_n4_bz128_step60
8B • Updated • 10
ScaleML-RLHF/qwmathbase_raftpp_bz128_step120
8B • Updated • 10
ScaleML-RLHF/qwmathbase_full_raft_step220
8B • Updated • 11
ScaleML-RLHF/qwmathbase_raftpp_bz128_step60
8B • Updated • 10
ScaleML-RLHF/qwmathbase_ppo_n1_step100
8B • Updated • 11
ScaleML-RLHF/qwmathbase_ppo_n1_step220
8B • Updated • 10
ScaleML-RLHF/qwmathbase_raw_raft_step240
8B • Updated • 11
ScaleML-RLHF/qwmathbase_ppo_n1_step180
8B • Updated • 10
ScaleML-RLHF/qwmathbase_ppo_n1_step80
8B • Updated • 10
ScaleML-RLHF/qwmathbase_raw_raft_step320
8B • Updated • 12
ScaleML-RLHF/qwmathbase_full_raft_step20
8B • Updated • 11
ScaleML-RLHF/qwmathbase_raftpp_bz128_step40
8B • Updated • 11
ScaleML-RLHF/qwmathbase_full_raft_step40
8B • Updated • 11