open-compass / open-compass/opencompass
[Feature] 直接在第三方脚本中启动评测
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 7.5k
- Forks
- 869
- Avg merge
- 17h 52m
- Merged PRs (30d)
- 13
Description
描述该功能
我已经在自己的脚本里有一个量化后的model实例了，我如何启动直接启动评测而不是重新在命令行中用python run.py方法加载model
就跟lm-eval支持的一样
是否希望自己实现该功能？
- 我希望自己来实现这一功能，并向 OpenCompass 贡献代码！
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading run.py and tracing how it loads a model before evaluation begins. Define the supported entry point for passing an already-created quantized model from a third-party script, then verify that evaluation runs without reloading it through the command line.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100