jdopensource

/

JoyAI-LLM-Flash

like 82

Follow

JD Open Source 74

Evaluation Results

    This PR adds evaluation results extracted from the Model Card.

    **Benchmarks:**
    - MMLU-Pro: 81.02

• GPQA-Diamond: 74.43

    **Files created:**
    - .eval_results/mmlu_pro.yaml
  

• .eval_results/gpqa_diamond.yaml

    ---
  
    Extracted automatically using the [LLM-powered evaluation extractor](https://github.com/huggingface/community-evals).