该模型基于[YeungNLP/Ziya-LLaMA-13B-Pretrain-v1](https://huggingface.co/YeungNLP/Ziya-LLaMA-13B-Pretrain-v1)，使用百万中英文指令数据，进行指令微调。

更多详情请查看[Firefly项目](https://github.com/yangjianxin1/Firefly)
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_YeungNLP__firefly-ziya-13b)

| Metric                | Value                     |
|-----------------------|---------------------------|
| Avg.                  | 47.58   |
| ARC (25-shot)         | 55.38          |
| HellaSwag (10-shot)   | 78.47    |
| MMLU (5-shot)         | 45.18         |
| TruthfulQA (0-shot)   | 49.29   |
| Winogrande (5-shot)   | 74.82   |
| GSM8K (5-shot)        | 6.9        |
| DROP (3-shot)         | 23.01         |