liuwenhan
/

triviaqa_hotpotqa_train-search-r1-ppo-qwen2.5-7b-em-iter1

Model card Files Files and versions

No model card

Downloads last month: 8

Safetensors

Model size

8B params

Tensor type

F32

·

Inference Providers NEW

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

Collection including liuwenhan/triviaqa_hotpotqa_train-search-r1-ppo-qwen2.5-7b-em-iter1

Agentic-R

Our trained retriever Agentic-R and search agent • 6 items • Updated Jan 23 • 3