lmdeploy部署

最新推荐文章于 2024-08-01 20:59:33 发布

h52013141

最新推荐文章于 2024-08-01 20:59:33 发布

阅读量179

点赞数 9

文章标签：人工智能

本文链接：https://blog.csdn.net/h52013141/article/details/139890916

版权

创建conda环境

studio-conda -t lmdeploy -o pytorch-2.1.2
在这里插入图片描述

安装LMDeploy

conda activate lmdeploy
pip install lmdeploy[all]==0.3.0
在这里插入图片描述

LMDeploy模型对话(chat)

下载模型

ls /root/share/new_models/Shanghai_AI_Laboratory/

cd ~
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)

conda activate lmdeploy

python /root/pipeline_transformer.py
在这里插入图片描述