PeterJinGo
/

SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-ppo

Model card Files Files and versions Community

No model card

Downloads last month: 1,815

Safetensors

Model size

7.62B params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-ppo

Quantizations

Collection including PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-ppo

Search-R1

Preliminary checkpoints with outcome-only RL. • 14 items • Updated Apr 7 • 9