liushz

For datasets on OpenCompass 1.0 Leaderboard, you can just move your cursor on the score of the dataset to find the config. For example, the config for C-Eval can be...

> > For datasets on OpenCompass 1.0 Leaderboard, you can just move your cursor on the score of the dataset to find the config. For example, the config for C-Eval...

Thanks for pointing this typo, we will refine it soon.

 like above cfg, you can set `model_kwargs=dict(tensor_parallel_size=8),` for your case.

Have you changed your partition logic midway? If you run it all at once, this problem shouldn't occur

The error log for your eval stage is because there are some errors during your infer stage, so the length of prediction is different with refs, you can check the...

Apologies for the confusion. We are currently utilizing the `flores200` dataset; however, the configuration `flores_gen_806ede` mistakenly employs the prompt for `flores100`. We will address and rectify this issue promptly.

For optimal performance, it is advisable to configure the `max_seq_len` parameter to the highest value feasible, such as 32768 or even higher if possible. As for the `max_out_len`, it typically...

What is your content in `eval_demo.py`? I use the default config: `/opencompass/configs/datasets/ARC_e/ARC_e_gen.py`, it works just fine.

Please add a default config named "mmmlu_gen.py" for chat model generation, with content like: ``` from mmengine.config import read_base with read_base(): from .mmmlu_gen_xxx.py import mmmlu_datasets # noqa: F401, F403 ```