L
Vicuna 7b V1.5
开源来自 LMSYS · 发布于 2023-07-29
10.9
平均分
N/A
输入价格
N/A
输出价格
N/A
上下文窗口
text-generation
类型
Tested on 6 benchmarks with 10.9% average. Top scores: IFEval (23.5%), BBH (HuggingFace) (15.2%), MMLU-PRO (12.7%).
基准测试分数
| 基准测试 | 类别 | 分数 | Bar |
|---|---|---|---|
| IFEval | language | 23.5 | |
| BBH (HuggingFace) | general | 15.2 | |
| MMLU-PRO | knowledge | 12.7 | |
| MUSR | reasoning | 11.4 | |
| MATH Level 5 | math | 1.4 | |
| GPQA | knowledge | 1.1 |