Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Paper • 2503.09516 • Published • 41
Search-R1
Preliminary checkpoints with outcome-only RL.
-
-
PeterJinGo/SearchR1-nq_hotpotqa_train-llama3.2-3b-em-ppo
4B • Updated • 18 -
PeterJinGo/SearchR1-nq_hotpotqa_train-llama3.2-3b-em-grpo
4B • Updated • 18 -
PeterJinGo/SearchR1-nq_hotpotqa_train-llama3.2-3b-it-em-ppo
4B • Updated • 76 -
PeterJinGo/SearchR1-nq_hotpotqa_train-llama3.2-3b-it-em-grpo
4B • Updated • 14 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo
3B • Updated • 1.33k • 1 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-grpo
3B • Updated • 95 • 1 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-ppo
3B • Updated • 76 • 1 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-grpo
3B • Updated • 96 • 1 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-ppo
8B • Updated • 1.58k • 6 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-it-em-ppo
8B • Updated • 1.15k -
PeterJinGo/wiki-18-corpus
Updated • 4.84k • 1 -
PeterJinGo/wiki-18-e5-index
Updated • 15.6k • 2 -
PeterJinGo/nq_hotpotqa_train
Viewer • Updated • 221k • 2.98k • 17 -
PeterJinGo/LICENCE
Viewer • Updated • 202 • 19