This model is a merged version of Qwen/Qwen2.5-7B-Instruct utilizing a novel model merging technique to optimize performance while maintaining robustness across tasks.

This model has been officially evaluated on open_llm_leaderboard, achieving the following results:

As of February 19, 2025, this model ranks 1st among all 7B and smaller models on open_llm_leaderboard.

For the latest and complete leaderboard rankings, please refer to the open_llm_leaderboard.

We will release details on the merging technique and methodology soon, Stay tuned for updates! 🚀