第5节 LMDeploy 量化部署 LLM 实践 作业

基础作业（结营必做）

完成以下任务，并将实现过程记录截图：

• 配置 LMDeploy 运行环境
• 以命令行方式与 InternLM2-Chat-1.8B 模型对话

创建conda环境

studio-conda -t lmdeploy -o pytorch-2.1.2

安装LMDeploy

conda activate lmdeploy

pip install lmdeploy[all]==0.3.0

LMDeploy模型对话(chat)

下载模型

ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b /root/
# cp -r /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b /root/

使用Transformer库运行模型

touch /root/pipeline_transformer.py

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("/root/internlm2-chat-1_8b", trust_remote_code=True)

# Set `torch_dtype=torch.float16` to load model in float16, otherwise it will be loaded as float32 and cause OOM Error.
model = AutoModelForCausalLM.from_pretrained("/root/internlm2-chat-1_8b", torch_dtype=torch.float16, trust_remote_code=True).cuda()
model = model.eval()

inp = "hello"
print("[INPUT]", inp)
response, history = model.chat(tokenizer, inp, history=[])
print("[OUTPUT]", response)

inp = "please provide three suggestions about time management"
print("[INPUT]", inp)
response, history = model.chat(tokenizer, inp, history=history)
print("[OUTPUT]", response)

python /root/pipeline_transformer.py

使用LMDeploy与模型对话

conda activate lmdeploy

lmdeploy chat /root/internlm2-chat-1_8b

刚开始的时候会有bug，响应不及时。生成第一个回复后，后续对话就比较流畅。