Qwen2-VLを試す

!pip install git+https://github.com/huggingface/transformers
!pip install qwen-vl-utils

from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2VLForConditionalGeneration.from_pretrained(
    #"Qwen/Qwen2-VL-2B-Instruct",
    "Qwen/Qwen2-VL-7B-Instruct",
    torch_dtype="auto",
    device_map="auto"
)

min_pixels = 512*28*28
max_pixels = 1024*28*28
processor = AutoProcessor.from_pretrained(
    #"Qwen/Qwen2-VL-2B-Instruct",
    "Qwen/Qwen2-VL-7B-Instruct",
    min_pixels=min_pixels,
    max_pixels=max_pixels
)

import requests

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "画像について詳しく説明してください。"},
        ],
    }
]

text = processor.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text], 
    images=image_inputs,
    videos=video_inputs,
    padding=True, 
    return_tensors="pt"
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=1024)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

min_pixels = 512*28*28
max_pixels = 1024*28*28
processor = AutoProcessor.from_pretrained(
    "Qwen/Qwen2-VL-2B-Instruct",
    min_pixels=min_pixels,
    max_pixels=max_pixels
)