PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo-v0.3
3B • Updated • 956
Search-R1-v0.3
RL with outcome reward + format reward. https://arxiv.org/abs/2505.15117
-
-
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-ppo-v0.3
3B • Updated • 14 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-grpo-v0.3
3B • Updated • 321 • 1 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-grpo-v0.3
3B • Updated • 85 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-ppo-v0.3
8B • Updated • 6.43k • 1 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-grpo-v0.3
8B • Updated • 1.2k -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-it-em-grpo-v0.3
8B • Updated • 26 • 1 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-14b-em-ppo-v0.3
15B • Updated • 41 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-14b-em-grpo-v0.3
15B • Updated • 3 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-14b-it-em-grpo-v0.3
15B • Updated • 182 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-32b-em-grpo-v0.3
33B • Updated • 7 -
PeterJinGo/LICENCE
Viewer • Updated • 202 • 9