diff --git a/README.md b/README.md index 80afa77e573131fd89ab7f794a0c7a1c807f0018..99f959dd421dd07a0e31b6b7fdb9798c043e9b55 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,21 @@ # llm-coding-eval -大模型写代码能力评测 \ No newline at end of file +大模型写代码能力评测 + +## 目录说明 + +* backup/ + * 最早版本的评测，测试例子来自真实的用户查询 + * 评测体系来自基本的分类 +* eval_set/ + * 体系化设计的评测用例 + * 从简单到复杂的编程粒度设计 +* llm_set/ + * 大模型配置列表，配置每一种大模型的元数据 +* src/ + * 评测源代码 +* mian.py 程序入口 + +## 同类评测项目 + +1. 斯坦福大学的评测：AlpacaEval Logo Leaderboard diff --git "a/AIGC\346\225\260\346\215\256\350\257\204\344\274\260.xlsx" "b/backup/AIGC\346\225\260\346\215\256\350\257\204\344\274\260.xlsx" similarity index 100% rename from "AIGC\346\225\260\346\215\256\350\257\204\344\274\260.xlsx" rename to "backup/AIGC\346\225\260\346\215\256\350\257\204\344\274\260.xlsx" diff --git a/data/llm-codeing.json b/backup/llm-codeing.json similarity index 100% rename from data/llm-codeing.json rename to backup/llm-codeing.json diff --git a/main.py b/main.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391