首先创建虚拟环境,安装必要的依赖
conda create -n opencompass123 python=3.10.10 -y
conda activate opencompass123
conda install pytorch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 pytorch-cuda=12.1 -c pytorch -c nvidia -y
# 注意:一定要先 cd /root
cd /root
git clone -b 0.2.4 https://github.com/open-compass/opencompass
cd opencompass
pip install -e .
apt-get update
apt-get install cmake -y
pip install -r requirements.txt
pip install protobuf
所有环境安装完成
进行数据准备
解压数据集
查看InternLM和ceval 相关的配置文件
使用使用命令行配置参数法进行评测
代码如下:
from opencompass.models import HuggingFaceCausalLM
models = [
dict(
type=HuggingFaceCausalLM,
abbr='internlm2-1.8b-hf',
path="/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b",
tokenizer_path='/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b',
model_kwargs=dict(
trust_remote_code=True,
device_map='auto',
),
tokenizer_kwargs=dict(
padding_side='left',
truncation_side='left',
use_fast=False,
trust_remote_code=True,
),
max_out_len=100,
min_out_len=1,
max_seq_len=2048,
batch_size=8,
run_cfg=dict(num_gpus=1, num_procs=1),
)
]
开始评测
#环境变量配置
export MKL_SERVICE_FORCE_INTEL=1
#或
export MKL_THREADING_LAYER=GNU
python run.py --datasets ceval_gen --models hf_internlm2_chat_1_8b --debug
经过了3个多小时,评测完成
接下来使用配置文件修改参数法进行评测
创建python文件,写入代码
from mmengine.config import read_base
with read_base():
from .datasets.ceval.ceval_gen import ceval_datasets
from .models.hf_internlm.hf_internlm2_chat_1_8b import models as hf_internlm2_chat_1_8b_models
datasets = ceval_datasets
models = hf_internlm2_chat_1_8b_models
启动评测
cd /root/opencompass
python run.py configs/eval_tutorial_demo.py --debug
评测完成(经过3个多小时)