mPLUG-Owl3

简介

mPLUG-Owl3 是一款先进的多模态大型语言模型，旨在应对长图像序列理解的挑战。我们提出了 Hyper Attention（超注意力机制），将多模态大型语言模型中的长视觉序列理解速度提升了六倍，使其能够处理长达八倍的视觉序列。同时，该模型在单图像、多图像及视频任务上仍保持着优异性能。

Github：mPLUG-Owl

快速开始

加载 mPLUG-Owl3。目前我们仅支持 ['sdpa', 'flash_attention_2'] 中的 attn_implementation。



import torch
from transformers import AutoConfig, AutoModel
model_path = 'mPLUG/mPLUG-Owl3-1B-241014'
config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
print(config)
# model = mPLUGOwl3Model(config).cuda().half()
model = AutoModel.from_pretrained(model_path, attn_implementation='sdpa', torch_dtype=torch.half, trust_remote_code=True)
model.eval().cuda()

与图像对话。

from PIL import Image

from transformers import AutoTokenizer, AutoProcessor
from decord import VideoReader, cpu 
model_path = 'mPLUG/mPLUG-Owl3-1B-241014'
tokenizer = AutoTokenizer.from_pretrained(model_path)
processor = model.init_processor(tokenizer)

image = Image.new('RGB', (500, 500), color='red')

messages = [
    {"role": "user", "content": """<|image|>
Describe this image."""},
    {"role": "assistant", "content": ""}
]

inputs = processor(messages, images=[image], videos=None)

inputs.to('cuda')
inputs.update({
    'tokenizer': tokenizer,
    'max_new_tokens':100,
    'decode_text':True,
})


g = model.generate(**inputs)
print(g)

与视频对话。

from PIL import Image

from transformers import AutoTokenizer, AutoProcessor
from decord import VideoReader, cpu    # pip install decord
model_path = 'mPLUG/mPLUG-Owl3-1B-241014'
tokenizer = AutoTokenizer.from_pretrained(model_path)
processor = model.init_processor(tokenizer)


messages = [
    {"role": "user", "content": """<|video|>
Describe this video."""},
    {"role": "assistant", "content": ""}
]

videos = ['/nas-mmu-data/examples/car_room.mp4']

MAX_NUM_FRAMES=16

def encode_video(video_path):
    def uniform_sample(l, n):
        gap = len(l) / n
        idxs = [int(i * gap + gap / 2) for i in range(n)]
        return [l[i] for i in idxs]

    vr = VideoReader(video_path, ctx=cpu(0))
    sample_fps = round(vr.get_avg_fps() / 1)  # FPS
    frame_idx = [i for i in range(0, len(vr), sample_fps)]
    if len(frame_idx) > MAX_NUM_FRAMES:
        frame_idx = uniform_sample(frame_idx, MAX_NUM_FRAMES)
    frames = vr.get_batch(frame_idx).asnumpy()
    frames = [Image.fromarray(v.astype('uint8')) for v in frames]
    print('num frames:', len(frames))
    return frames
video_frames = [encode_video(_) for _ in videos]
inputs = processor(messages, images=None, videos=video_frames)

inputs.to('cuda')
inputs.update({
    'tokenizer': tokenizer,
    'max_new_tokens':100,
    'decode_text':True,
})


g = model.generate(**inputs)
print(g)

引用

如果您发现我们的工作对您有所帮助，欢迎引用我们的成果。

@misc{ye2024mplugowl3longimagesequenceunderstanding,
      title={mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models}, 
      author={Jiabo Ye and Haiyang Xu and Haowei Liu and Anwen Hu and Ming Yan and Qi Qian and Ji Zhang and Fei Huang and Jingren Zhou},
      year={2024},
      eprint={2408.04840},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2408.04840}, 
}

简介

快速开始

加载 mPLUG-Owl3。目前我们仅支持 ['sdpa', 'flash_attention_2'] 中的 attn_implementation。



import torch
from transformers import AutoConfig, AutoModel
model_path = 'mPLUG/mPLUG-Owl3-1B-241014'
config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
print(config)
# model = mPLUGOwl3Model(config).cuda().half()
model = AutoModel.from_pretrained(model_path, attn_implementation='sdpa', torch_dtype=torch.half, trust_remote_code=True)
model.eval().cuda()

与图像对话。

from PIL import Image

from transformers import AutoTokenizer, AutoProcessor
from decord import VideoReader, cpu 
model_path = 'mPLUG/mPLUG-Owl3-1B-241014'
tokenizer = AutoTokenizer.from_pretrained(model_path)
processor = model.init_processor(tokenizer)

image = Image.new('RGB', (500, 500), color='red')

messages = [
    {"role": "user", "content": """<|image|>
Describe this image."""},
    {"role": "assistant", "content": ""}
]

inputs = processor(messages, images=[image], videos=None)

inputs.to('cuda')
inputs.update({
    'tokenizer': tokenizer,
    'max_new_tokens':100,
    'decode_text':True,
})


g = model.generate(**inputs)
print(g)

与视频对话。

from PIL import Image

from transformers import AutoTokenizer, AutoProcessor
from decord import VideoReader, cpu    # pip install decord
model_path = 'mPLUG/mPLUG-Owl3-1B-241014'
tokenizer = AutoTokenizer.from_pretrained(model_path)
processor = model.init_processor(tokenizer)


messages = [
    {"role": "user", "content": """<|video|>
Describe this video."""},
    {"role": "assistant", "content": ""}
]

videos = ['/nas-mmu-data/examples/car_room.mp4']

MAX_NUM_FRAMES=16

def encode_video(video_path):
    def uniform_sample(l, n):
        gap = len(l) / n
        idxs = [int(i * gap + gap / 2) for i in range(n)]
        return [l[i] for i in idxs]

    vr = VideoReader(video_path, ctx=cpu(0))
    sample_fps = round(vr.get_avg_fps() / 1)  # FPS
    frame_idx = [i for i in range(0, len(vr), sample_fps)]
    if len(frame_idx) > MAX_NUM_FRAMES:
        frame_idx = uniform_sample(frame_idx, MAX_NUM_FRAMES)
    frames = vr.get_batch(frame_idx).asnumpy()
    frames = [Image.fromarray(v.astype('uint8')) for v in frames]
    print('num frames:', len(frames))
    return frames
video_frames = [encode_video(_) for _ in videos]
inputs = processor(messages, images=None, videos=video_frames)

inputs.to('cuda')
inputs.update({
    'tokenizer': tokenizer,
    'max_new_tokens':100,
    'decode_text':True,
})


g = model.generate(**inputs)
print(g)

引用

如果您发现我们的工作对您有所帮助，欢迎引用我们的成果。

@misc{ye2024mplugowl3longimagesequenceunderstanding,
      title={mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models}, 
      author={Jiabo Ye and Haiyang Xu and Haowei Liu and Anwen Hu and Ming Yan and Qi Qian and Ji Zhang and Fei Huang and Jingren Zhou},
      year={2024},
      eprint={2408.04840},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2408.04840}, 
}