Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Paper
•
2503.09516
•
Published
•
30
Search-R1
Preliminary checkpoints with outcome-only RL.
-
-
PeterJinGo/SearchR1-nq_hotpotqa_train-llama3.2-3b-em-ppo
Updated • 212 -
PeterJinGo/SearchR1-nq_hotpotqa_train-llama3.2-3b-em-grpo
Updated • 2 -
PeterJinGo/SearchR1-nq_hotpotqa_train-llama3.2-3b-it-em-ppo
Updated • 14 -
PeterJinGo/SearchR1-nq_hotpotqa_train-llama3.2-3b-it-em-grpo
Updated • 10 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo
Updated • 136 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-grpo
Updated • 26 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-ppo
Updated • 23 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-grpo
Updated • 35 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-ppo
Updated • 4.08k -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-it-em-ppo
Updated • 375 -
PeterJinGo/wiki-18-corpus
Updated • 1.76k -
PeterJinGo/wiki-18-e5-index
Updated • 2.4k -
PeterJinGo/nq_hotpotqa_train
Viewer • Updated • 221k • 422 • 2