OpenCompass 评测 InternLM-1.8B
环境配置
创建conda环境
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 -r requirements.txt
pip install protobuf
数据准备
解压评测数据集到 data/ 处
cp /share/temp/datasets/OpenCompassData-core-20231110.zip ./
unzip OpenCompassData-core-20231110.zip
启动评测 (10% A100 8GB 资源)
export MKL_SERVICE_FORCE_INTEL=1
export MKL_THREADING_LAYER=GNU
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
命令解析
python run.py
--datasets ceval_gen \
--hf-path /share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b \ # HuggingFace 模型路径
--tokenizer-path /share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b \ # HuggingFace tokenizer 路径(如果与模型路径相同,可以省略)
--tokenizer-kwargs padding_side='left' truncation='left' trust_remote_code=True \ # 构建 tokenizer 的参数
--model-kwargs device_map='auto' trust_remote_code=True \ # 构建模型的参数
--max-seq-len 1024 \ # 模型可以接受的最大序列长度
--max-out-len 16 \ # 生成的最大 token 数
--batch-size 2 \ # 批量大小
--num-gpus 1 # 运行模型所需的 GPU 数量
--debug