LLaVA-NeXT-Video 模型卡片

import av
import torch
from transformers import LlavaNextVideoProcessor, LlavaNextVideoForConditionalGeneration

model_id = "llava-hf/LLaVA-NeXT-Video-34B-hf"

model = LlavaNextVideoForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True, 
).to(0)

processor = LlavaNextVideoProcessor.from_pretrained(model_id)

def read_video_pyav(container, indices):
    '''
    Decode the video with PyAV decoder.
    Args:
        container (`av.container.input.InputContainer`): PyAV container.
        indices (`List[int]`): List of frame indices to decode.
    Returns:
        result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3).
    '''
    frames = []
    container.seek(0)
    start_index = indices[0]
    end_index = indices[-1]
    for i, frame in enumerate(container.decode(video=0)):
        if i > end_index:
            break
        if i >= start_index and i in indices:
            frames.append(frame)
    return np.stack([x.to_ndarray(format="rgb24") for x in frames])


# define a chat history and use `apply_chat_template` to get correctly formatted prompt
# Each value in "content" has to be a list of dicts with types ("text", "image", "video") 
conversation = [
    {

        "role": "user",
        "content": [
            {"type": "text", "text": "Why is this video funny?"},
            {"type": "video"},
            ],
    },
]

prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)

video_path = hf_hub_download(repo_id="raushan-testing-hf/videos-test", filename="sample_demo_1.mp4", repo_type="dataset")
container = av.open(video_path)

# sample uniformly 8 frames from the video, can sample more for longer videos
total_frames = container.streams.video[0].frames
indices = np.arange(0, total_frames, total_frames / 8).astype(int)
clip = read_video_pyav(container, indices)
inputs_video = processor(text=prompt, videos=clip, padding=True, return_tensors="pt").to(model.device)

output = model.generate(**inputs_video, max_new_tokens=100, do_sample=False)
print(processor.decode(output[0][2:], skip_special_tokens=True))

import requests
from PIL import Image

conversation = [
    {
      "role": "user",
      "content": [
          {"type": "text", "text": "What are these?"},
          {"type": "image"},
        ],
    },
]
prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)

image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"
raw_image = Image.open(requests.get(image_file, stream=True).raw)
inputs_image = processor(text=prompt, images=raw_image, return_tensors='pt').to(0, torch.float16)

output = model.generate(**inputs_video, max_new_tokens=100, do_sample=False)
print(processor.decode(output[0][2:], skip_special_tokens=True))

conversation_1 = [
    {
      "role": "user",
      "content": [
          {"type": "text", "text": "What's the content of the image>"},
          {"type": "image"},
        ],
    }
]
conversation_2 = [
    {
      "role": "user",
      "content": [
          {"type": "text", "text": "Why is this video funny?"},
          {"type": "video"},
        ],
    },
]
prompt_1 = processor.apply_chat_template(conversation_1, add_generation_prompt=True)
prompt_2 = processor.apply_chat_template(conversation_2, add_generation_prompt=True)

s = processor(text=[prompt_1, prompt_2], images=image, videos=clip, padding=True, return_tensors="pt").to(model.device)

# Generate
generate_ids = model.generate(**inputs, max_new_tokens=100)
out = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
print(out)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://www.ilankelman.org/stopsigns/australia.jpg"}
            {"type": "video", "path": "my_video.mp4"},
            {"type": "text", "text": "What is shown in this image and video?"},
        ],
    },
]

inputs = processor.apply_chat_template(messages, num_frames=8, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors"pt")
output = model.generate(**inputs, max_new_tokens=50)

model = LlavaNextVideoForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True,
+   load_in_4bit=True
)

model = LlavaNextVideoForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True,
+   use_flash_attention_2=True
).to(0)

@misc{zhang2024llavanextvideo,
  title={LLaVA-NeXT: A Strong Zero-shot Video Understanding Model},
  url={https://llava-vl.github.io/blog/2024-04-30-llava-next-video/},
  author={Zhang, Yuanhan and Li, Bo and Liu, haotian and Lee, Yong jae and Gui, Liangke and Fu, Di and Feng, Jiashi and Liu, Ziwei and Li, Chunyuan},
  month={April},
  year={2024}
}

@misc{liu2024llavanext,
    title={LLaVA-NeXT: Improved reasoning, OCR, and world knowledge},
    url={https://llava-vl.github.io/blog/2024-01-30-llava-next/},
    author={Liu, Haotian and Li, Chunyuan and Li, Yuheng and Li, Bo and Zhang, Yuanhan and Shen, Sheng and Lee, Yong Jae},
    month={January},
    year={2024}
}