语言: 阿拉伯语
许可证: 其他
标签:

• 视觉
• 图像描述生成
  管道类型: 图像转文本

🦚 孔雀模型

🦚 孔雀模型是基于InstructBLIP架构的阿拉伯语多模态大语言模型，其语言模型采用AraLLaMA。该模型在论文《孔雀：阿拉伯语多模态大语言模型家族与评测基准》(https://arxiv.org/abs/2403.01031)中首次提出。

使用方法

使用方式如下：

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

model = InstructBlipForConditionalGeneration.from_pretrained("UBC-NLP/Peacock")
processor = InstructBlipProcessor.from_pretrained("UBC-NLP/Peacock")
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

url = "https://upload.wikimedia.org/wikipedia/commons/8/83/Socotra_dragon_tree.JPG"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
prompt = "描述这张图片"
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)

引用

若使用本模型，请引用以下论文：

@inproceedings{alwajih2024peacock,
  title = {Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks},
  author = {Alwajih, Fakhraddin and Nagoudi, El Moatez Billah and Bhatia, Gagan and Mohamed, Abdelrahman and Abdul-Mageed, Muhammad},
  booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  pages = {12753--12776},
  year = {2024},
  address = {Bangkok, Thailand},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.acl-long.689}
}