Qwen2.5-7B-CABS-v0.4: A Merged Model Using a Novel Technique

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.

Official Performance

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

IFEVAL BBH MATH GPQA MUSR MMLU-PRO AVG
75.83 36.36 48.39 7.72 15.17 37.73 36.88

As of February 19, 2025, this model ranks 2nd among all 7B and smaller models on open_llm_leaderboard.

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

Recipe Coming Soon

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

Downloads last month
92
Safetensors
Model size
7.62B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for gz987/qwen2.5-7b-cabs-v0.4

Base model

Qwen/Qwen2.5-7B
Finetuned
(750)
this model
Merges
6 models
Quantizations
2 models