Mplug Owl3 1B 241014

🚀 mPLUG-Owl3

mPLUG-Owl3 is a cutting - edge multi - modal large language model crafted to address the difficulties of long image sequence understanding. It introduces Hyper Attention, which accelerates the speed of long visual sequence understanding in multimodal large language models by six times, enabling the processing of visual sequences eight times longer. Moreover, it maintains outstanding performance on single - image, multi - image, and video tasks.

Github: mPLUG-Owl

🚀 Quick Start

Load the mPLUG-Owl3

We currently only support attn_implementation in ['sdpa', 'flash_attention_2'].

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()

Chat with images

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)

Chat with a video

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)

📄 License

This project is licensed under the Apache-2.0 license.

📚 Citation

If you find our work helpful, feel free to give us a cite.

@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}, 
}