Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Paper
•
2503.09516
•
Published
•
32
Search-R1
Preliminary checkpoints with outcome-only RL.
-
-
PeterJinGo/SearchR1-nq_hotpotqa_train-llama3.2-3b-em-ppo
4B • Updated • 63 -
PeterJinGo/SearchR1-nq_hotpotqa_train-llama3.2-3b-em-grpo
4B • Updated • 21 -
PeterJinGo/SearchR1-nq_hotpotqa_train-llama3.2-3b-it-em-ppo
4B • Updated • 10 -
PeterJinGo/SearchR1-nq_hotpotqa_train-llama3.2-3b-it-em-grpo
4B • Updated • 34 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo
3B • Updated • 79 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-grpo
3B • Updated • 33 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-ppo
3B • Updated • 22 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-grpo
3B • Updated • 1.84k -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-ppo
8B • Updated • 4.01k • 3 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-it-em-ppo
8B • Updated • 1.81k -
PeterJinGo/wiki-18-corpus
Updated • 772 -
PeterJinGo/wiki-18-e5-index
Updated • 1.76k -
PeterJinGo/nq_hotpotqa_train
Viewer • Updated • 221k • 682 • 5