YYYYYYibo/qwen3-4b-questa-nonmcq-estep-pos20-neg20-truncneg20-step50
Text Generation • 4B • Updated • 161
Wang
YYYYYYibo
AI & ML interests
None yet
Recent Activity
published a model 3 days ago
YYYYYYibo/qwen3-4b-questa-nonmcq-estep-pos20-neg20-truncneg20-step50 updated a model 3 days ago
YYYYYYibo/qwen3-4b-questa-nonmcq-estep-pos20-neg20-truncneg20-step50 updated a dataset 4 days ago
YYYYYYibo/QuestA-OpenR1-Math-220k-JoinedOrganizations
None yet
models 131
YYYYYYibo/qwen3-4b-dapo-estep-pos5-neg5-truncneg5-b256-step50
4B • Updated • 39
YYYYYYibo/olmo3-7b-openthoughts-estep-pos5-neg5
7B • Updated • 6
YYYYYYibo/Qwen3-4B-Teacher-Penalty-PPO-Step50
4B • Updated • 5
YYYYYYibo/Qwen3-4B-Teacher-Penalty-PPO-Step25
4B • Updated • 14
YYYYYYibo/qwen2_5_7b_sft_baseline
8B • Updated • 3
YYYYYYibo/qwen2_7b_grpo_vanilla_0325_1257
8B • Updated • 4
YYYYYYibo/qwen2_7b_grpo_replay_hard_40percent_0326_0024
8B • Updated • 3
YYYYYYibo/qwen2-7b-grpo-replay-hard-25percent-0326
8B • Updated • 3
YYYYYYibo/simple_online_epoch_2_dpo_iter_6
7B • Updated • 4
datasets 353
YYYYYYibo/QuestA-OpenR1-Math-220k-Joined
Viewer • Updated • 12.5k • 35
YYYYYYibo/DAPO-Math-17k-Qwen3-235B-A22B-Thinking-2507-non-thinking-dedup
Viewer • Updated • 15.1k • 80
YYYYYYibo/qwen3-8b-base-deepscaler-rollouts
Viewer • Updated • 80k • 41
YYYYYYibo/alfworld-experimenter-gpt5mini-sft-1k
Viewer • Updated • 1k • 86
YYYYYYibo/alfworld-expert-prefix-rollouts
Viewer • Updated • 194k • 89
YYYYYYibo/VSR-MATH500-Qwen2.5-7B-Rollouts
Updated • 84
YYYYYYibo/qwen3-4b-nonthinking-skywork-rollouts-verified
Viewer • Updated • 215k • 23
YYYYYYibo/alfworld-success-trajs
Viewer • Updated • 3.46k • 7
YYYYYYibo/openr1-math-220k-hard-qwen2-5-7b-instruct-1k-with-successful-traj
Viewer • Updated • 1.23k • 7
YYYYYYibo/openr1-math-220k-hard-qwen2-5-7b-instruct-1k
Viewer • Updated • 1.23k • 7