该模型使用bloom-7b1，使用百万中英文指令数据，进行指令微调。
更多详情见Firefly项目
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 34.99 |
| ARC (25-shot) | 40.44 |
| HellaSwag (10-shot) | 61.2 |
| MMLU (5-shot) | 26.83 |
| TruthfulQA (0-shot) | 40.83 |
| Winogrande (5-shot) | 64.56 |
| GSM8K (5-shot) | 0.68 |
| DROP (3-shot) | 10.37 |