qwen_vl_chat_inference.py

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig

# 如果您希望结果可复现，可以设置随机数种子。
# torch.manual_seed(1234)

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-VL-Chat", trust_remote_code=True)

model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-VL-Chat", device_map="cuda", trust_remote_code=True).eval()
model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-VL-Chat", trust_remote_code=True)

query = tokenizer.from_list_format([
    {'image': 'assets/mm_tutorial/Rebecca_(1939_poster).jpeg'},
    {'text': 'What is the name of the movie in the poster?'},
])

"""
 query = tokenizer.from_list_format([
  {'text': 'Who directed this movie?'},
])
response, history = model.chat(tokenizer, query=query, history=history)
print(response)

"""
response, history = model.chat(tokenizer, query=query, history=None)
print(response)