Junming Yang
Junming Yang
应该是模型导致的，如果是我们已经支持的模型，请提供具体的运行命令及模型名称；如果是自定义的模型，请检查模型。
The problem appears to be caused by the MiniCPM-Llama3-V-2_5 model.
Can you provide the running command?
If you are evaluating a private benchmark, please check your dataset file `xxx. tsv` fields correct, such as 'answer' instead of 'ans'. Please refer to [Development Doc](https://github.com/open-compass/VLMEvalKit/blob/main/docs/en/Development.md) for more detailed...
I try to reproduce this error. This is my command `torchrun --nproc-per-node=8 run.py --model InternVL-Chat-V1-5 --data MME`. Everything is OK. And **MME** benchmark should correspond to the `image_yorn.py` file instead...
Maybe you can try to pull our latest code. We have fixed some known minor bugs. If you still encounter other problems, please do not hesitate to contact us and...
手动下载：查看对应 vlmeval.dataset 中，对应 dataset 名的 `DATASET_URL` 链接，通过wget进行下载； 配置路径：在 .env 文件中设置 `LMUData=/path/to/your/dataset`。
Hi, @liuchunming033. 请检查下是否有足够的显存运行模型
Hi, @weikaih04. We found that TaskMeAnything_v1_imageqa_random has a minor typo. The field of tsv file spelled category incorrectly, resulting in the final calculation result can only output the overall score,...
same issue