部署Qwen2.5-VL-7B-Instruct-GPTQ-Int3

一只齐刘海的猫2025-08-22 19:41

模型下载

python 复制代码

from modelscope import snapshot_download
model_dir = snapshot_download('ChineseAlpacaGroup/Qwen2.5-VL-7B-Instruct-GPTQ-Int3')

相关包导入

python 复制代码

import os
import numpy as np
import pandas as pd
from tqdm import tqdm
from datetime import datetime,timedelta
from functools import wraps
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation.utils import GenerationConfig

模型配置

python 复制代码

model_path = "/modelscope/hub/models/ChineseAlpacaGroup/Qwen2.5-VL-7B-Instruct-GPTQ-Int3"
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="cuda", trust_remote_code=True,use_safetensors=True).eval()

模型调用

python 复制代码

query = tokenizer.from_list_format([
    {'image': 'https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg'},
    {'text': '这是什么'},
])
response, history = model.chat(tokenizer, query=query, history=None)
print(response)