评测流程:配置 -> 推理 -> 评估 -> 可视化
1. 环境配置
conda create -n opencompass python=3.10
conda activate opencompass
conda install pytorch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 pytorch-cuda=12.1 -c pytorch -c nvidia -y
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
pip install -r requirements.txt
pip install protobuf
2. 数据准备
cp /share/temp/datasets/OpenCompassData-core-20231110.zip /root/opencompass/
unzip OpenCompassData-core-20231110.zip
#查看评估配置
python tools/list_configs.py internlm ceval
数据结构和内容
3. 启动评测--8G显存即可
准备配置文件hf_internlm2_chat_1_8b.py
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),
)
]
执行
#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
时间较长耐心等待
评测结果
如何修改参数?
新建配置文件
cd /root/opencompass/configs
touch eval_tutorial_demo.py
贴入以下代码
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
参照此方法即可
执行评测