作业链接: Tutorial/opencompass/homework.md at camp2 · InternLM/Tutorial · GitHub
模型评估实战
* 环境配置
studio-conda -o internlm-base -t opencompass
source activate opencompass
安装opencompass
git clone -b 0.2.4 https://github.com/open-compass/opencompass
cd opencompass
pip install -e .
准备数据
cp /share/temp/datasets/OpenCompassData-core-20231110.zip /root/opencompass/
unzip OpenCompassData-core-20231110.zip
启动评测
```
python run.py --datasets ceval_gen --hf-path /share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b --tokenizer-path /share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b --tokenizer-kwargs padding_side='left' truncation='left' trust_remote_code=True --model-kwargs trust_remote_code=True device_map='auto' --max-seq-len 1024 --max-out-len 16 --batch-size 2 --num-gpus 1 --debug
```
过程截图如下
评测结果显示如下
可以看到 summary 和csv被分别写入。