MMBench评估代码报错

InternLM / InternLM-XComposer

InternLM-XComposer2 is a groundbreaking vision-language large model (VLLM) excelling in free-form text-image composition and comprehension.

1.91k stars 120 forks source link

MMBench评估代码报错 #298

Closed sczlmy closed 2 months ago

sczlmy commented 2 months ago

InternLM-XComposer-main/evaluation/mmbench目录下执行： CUDA_VISIBLE_DEVICES=0 python -u eval.py 报错 ImportError: cannot import name 'generate_answer' from 'utils'

LightDXY commented 2 months ago

thanks for the report, it should be `model_gen', we have fixed it.