InstructBLIP模型

使用 Vicuna-13b 作为语言模型的InstructBLIP模型。InstructBLIP是在Dai等人的论文 InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning 中介绍的。

免责声明：发布InstructBLIP模型的团队没有为该模型撰写模型卡片，因此该模型卡片由Hugging Face团队撰写。

模型描述

InstructBLIP是 BLIP-2 的视觉指导版本。详细信息请参阅论文。

预期用途和限制

使用方法如下：

from transformers import InstructBlipProcessor, InstructBlipForConditionalGeneration
import torch
from PIL import Image
import requests

model = InstructBlipForConditionalGeneration.from_pretrained("Salesforce/instructblip-vicuna-13b")
processor = InstructBlipProcessor.from_pretrained("Salesforce/instructblip-vicuna-13b")

device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

url = "https://raw.githubusercontent.com/salesforce/LAVIS/main/docs/_static/Confusing-Pictures.jpg"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
prompt = "What is unusual about this image?"
inputs = processor(images=image, text=prompt, return_tensors="pt").to(device)

outputs = model.generate(
        **inputs,
        do_sample=False,
        num_beams=5,
        max_length=256,
        min_length=1,
        top_p=0.9,
        repetition_penalty=1.5,
        length_penalty=1.0,
        temperature=1,
)
generated_text = processor.batch_decode(outputs, skip_special_tokens=True)[0].strip()
print(generated_text)

如何使用

有关代码示例，请参阅 documentation 。