EM-RAFT

community

AI & ML interests

None defined yet.

Recent Activity

FlippyDora submitted a paper 4 days ago

Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models

FlippyDora authored a paper 2 months ago

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

FlippyDora submitted a paper 2 months ago

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

View all activity

ScaleML-RLHF 's models 260

ScaleML-RLHF/qwmathbase_full_raft_step40

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raf_raft_n4_bz128_step140

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_weighted_sft_bz512_step20

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_non_neg_grpo_step20

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_weighted_sft_bz512_step180

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raf_raft_n4_bz128_step160

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raw_raft_step60

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raftpp_bz128_step140

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_full_raft_step220

8B • Updated Mar 20, 2025

ScaleML-RLHF/qwmathbase_ppo_n1_step220

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_weighted_sft_bz512_step100

8B • Updated Mar 20, 2025

ScaleML-RLHF/qwmathbase_grpo_n4_bz512_step120

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raw_raft_step120

8B • Updated Mar 20, 2025

ScaleML-RLHF/qwmathbase_raw_raft_step100

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_weighted_sft_bz512_step80

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_non_neg_grpo_step220

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_ppo_n1_step100

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raw_raft_step180

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_full_raft_step140

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_full_raft_step160

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_non_neg_grpo_step100

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raw_raft_step280

8B • Updated Mar 20, 2025

ScaleML-RLHF/qwmathbase_grpo_n4_bz512_step140

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_grpo_n4_bz512_step20

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_weighted_sft_bz512_step200

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raftpp_bz128_step160

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_raf_raft_n4_bz128_step40

8B • Updated Mar 20, 2025

ScaleML-RLHF/qwmathbase_full_raft_step100

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_weighted_sft_bz512_step120

8B • Updated Mar 20, 2025 • 1

ScaleML-RLHF/qwmathbase_non_neg_grpo_step80

8B • Updated Mar 20, 2025 • 1