PeterJinGo/R1-nq_hotpotqa_train-qwen2.5-3b-em-ppo-v0.2
Updated
•
35
Search-R1-v0.2
Exploration with a more stable RL pipeline with outcome-only reward and scaled-up LLMs. https://arxiv.org/abs/2503.09516
-
-
PeterJinGo/R1-nq_hotpotqa_train-qwen2.5-3b-it-em-ppo-v0.2
Updated • 9 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo-v0.2
Updated • 1.3k • 1 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-ppo-v0.2
Updated • 3 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-grpo-v0.2
Updated • 6 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-grpo-v0.2
Updated • 317 • 1 -
PeterJinGo/R1-nq_hotpotqa_train-qwen2.5-7b-em-ppo-v0.2
Updated • 110 -
PeterJinGo/R1-nq_hotpotqa_train-qwen2.5-7b-it-em-ppo-v0.2
Updated • 2 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-ppo-v0.2
Updated • 827 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-it-em-ppo-v0.2
Updated • 3 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-grpo-v0.2
Updated • 3 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-it-em-grpo-v0.2
Updated • 10 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-grpo-groupsize1-v0.2
Updated -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-grpo-groupsize3-v0.2
Updated -
PeterJinGo/R1-nq_hotpotqa_train-qwen2.5-14b-em-ppo-v0.2
Updated • 1 -
PeterJinGo/R1-nq_hotpotqa_train-qwen2.5-14b-it-em-ppo-v0.2
Updated • 1 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-14b-em-ppo-v0.2
Updated • 120 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-14b-it-em-ppo-v0.2
Updated • 2 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-14b-em-grpo-groupsize1-v0.2
Updated • 2 -
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-14b-it-em-grpo-groupsize1-v0.2
Updated • 28 -
PeterJinGo/wiki-18-corpus
Updated • 1.47k -
PeterJinGo/wiki-18-e5-index
Updated • 1.97k -
PeterJinGo/wiki-18-e5-index-HNSW64
Updated • 142 -
PeterJinGo/wiki-18-bm25-index
Updated • 84 -
PeterJinGo/nq_hotpotqa_train
Viewer • Updated • 221k • 366 • 2