Skip to content

Fix URLs in README for eval_model.py and bench_serving.sh #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
relic-yuexi wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −2
Open

Fix URLs in README for eval_model.py and bench_serving.sh #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,7 +107,7 @@ docker run -d \

## eval\_model.py

下载地址：https://github.com/OpenBMB/SOAR-Toolkit/blob/main/eval\_model.py
下载地址：https://github.com/OpenBMB/SOAR-Toolkit/blob/main/eval_model.py

`eval_model.py` 会通过调用已启动的 SGLang 推理服务，根据不同评测任务类型，给出模型在正确性上的评测分数。首先需要启动 SGLang 服务，并传入模型所使用的api\_base：

Expand Down Expand Up @@ -139,7 +139,7 @@ python3 eval_model.py \

## bench\_serving.sh

下载方式：https://github.com/OpenBMB/SOAR-Toolkit/blob/main/bench\_serving.sh
下载方式：https://github.com/OpenBMB/SOAR-Toolkit/blob/main/bench_serving.sh

本脚本使用 sglang 官方 bench\_serving 工具，在 3 档并发度下分别跑完所有评测请求，记录 Benchmark Duration。在对应档位传入数据集路径可以完成对应档位的测试，未输入数据集路径的可跳过该档位的测试，相关传参及说明对应如下：

Expand Down