Pinned Loading

1. RUC-GSAI/YuLan-Mini RUC-GSAI/YuLan-Mini Public

   A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.

   Python 235 20

2. RUCAIBox/R1-Searcher RUCAIBox/R1-Searcher Public

   R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

   Python 727 44

3. RUCAIBox/SimpleDeepSearcher RUCAIBox/SimpleDeepSearcher Public

   SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis

   Python 121 8

4. RUCAIBox/R1-Searcher-plus RUCAIBox/R1-Searcher-plus Public

   R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning

   Python 84 2

5. UI-TARS UI-TARS Public

   Forked from bytedance/UI-TARS

   Python

6. RUCAIBox/SWE-Master RUCAIBox/SWE-Master Public

   SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

   HTML 106 7