Commit aeb9899d authored by gaoqiong's avatar gaoqiong
Browse files

增加完善lmdeploy测评步骤

parent 8b3db123
...@@ -75,6 +75,24 @@ python run.py configs/eval_llama2_vllm.py ...@@ -75,6 +75,24 @@ python run.py configs/eval_llama2_vllm.py
2、使用lmdeploy推理验证 2、使用lmdeploy推理验证
```shell ```shell
#安装gpufusion 相关工具
#https://forum.hpccube.com/thread/483 进入网页下载gpufusion工具
#解压至dtk-24.04
unzip gpufusion.zip -d /opt/dtk-24.04/
#激活相关环境变量
source /opt/dtk-24.04/env.sh
source /opt/dtk/cuda/env.sh
#进入opencompass进行评测
cd opencompass
#fp16精度评测方法
python run.py configs/eval_llama2_lmdeploy.py
#awq int4 评测方法
#首先需要转换awqInt4模型
#model_name:模型名字如 llama2 qwen-7b
#awq_modelpath:awq 模型路径,例如:/dataset/llm-models/qwen/qwen-chat-7b-AWQ-4bit
#awq_lmdeploymodel_path:生成的lmdeploy格式 awq模型路径
lmdeploy convert ${model_name} ${awq_modelpath} --model-format awq --group-size 128 --dst-path ${awq_lmdeploymodel_path}
#将eval_llama2_lmdeploy.py中的Llama-2-7b-hf 替换为转换好的awq_lmdeploymodel_path
python run.py configs/eval_llama2_lmdeploy.py python run.py configs/eval_llama2_lmdeploy.py
``` ```
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment