-
Notifications
You must be signed in to change notification settings - Fork 405
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.
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
[Feature] Add dingo test #1529
base: main
Are you sure you want to change the base?
[Feature] Add dingo test #1529
Conversation
@@ -0,0 +1,41 @@ | |||
from mmengine.config import read_base |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
补充一下新增PR功能说明,和测试记录吧
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
title也修改成[feature] Add xxx 这样的格式吧
opencompass/datasets/dingo.py
Outdated
def score(self, origin_prompt: List, predictions: List) -> dict: | ||
current_time = time.strftime('%Y%m%d_%H%M%S', time.localtime()) | ||
file_data = [{'prompt':pmt, 'prediction':prd} for pmt, prd in zip(origin_prompt, predictions)] | ||
file_name = 'dingo_file_' + current_time + '.jsonl' |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这个要看看有没有更好的实现方式
input_data = { | ||
"eval_models": ["llm_base"], | ||
"input_path": file_name, | ||
"output_path": "./outputs/dingo/", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这个看看有没有全局的环境变量
Also please fix the lint issue with pre-commit hook |
Motivation
Add the test ability for data produced by llm.
Modification
Add eval_dingo.py in configs and ding.py in datasets.
Use cases (Optional)
model config:
result
dingo_benc.zip
eval_dingo_20240914_135811.zip
dingo_result.zip
Checklist
Before PR:
After PR: