LongVU_Qwen2_7B / README.md
Vision-CAIR's picture
Update README.md
d69cfa6 verified
|
raw
history blame
3.29 kB
metadata
datasets:
  - shenxq/OneVision
  - shenxq/VideoChat2
base_model:
  - Qwen/Qwen2-7B-Instruct
  - Vision-CAIR/LongVU_Qwen2_7B_img
model-index:
  - name: llava-onevision-qwen-7b-ov
    results:
      - task:
          type: multimodal
        dataset:
          name: EgoSchema
          type: egoschema
        metrics:
          - type: accuracy
            value: 67.6
            name: accuracy
            verified: true
      - task:
          type: multimodal
        dataset:
          name: MLVU
          type: mlvu
        metrics:
          - type: accuracy
            value: 65.4
            name: accuracy
            verified: true
      - task:
          type: multimodal
        dataset:
          name: MVBench
          type: mvbench
        metrics:
          - type: accuracy
            value: 66.9
            name: accuracy
            verified: true
      - task:
          type: multimodal
        dataset:
          name: VideoMME
          type: videomme
        metrics:
          - type: accuracy
            value: 60.6
            name: accuracy
            verified: true

LongVU

Play with the model on the HF demo.

Demo GIF

Use

We provide the simple generation process for using our model. For more details, you could refer to Github

# git clone https://github.com/Vision-CAIR/LongVU
import numpy as np
import torch
from longvu.builder import load_pretrained_model
from longvu.constants import (
    DEFAULT_IMAGE_TOKEN,
    IMAGE_TOKEN_INDEX,
)
from longvu.conversation import conv_templates, SeparatorStyle
from longvu.mm_datautils import (
    KeywordsStoppingCriteria,
    process_images,
    tokenizer_image_token,
)
from decord import cpu, VideoReader

tokenizer, model, image_processor, context_len = load_pretrained_model(
    "./checkpoints/longvu_qwen", None, "cambrian_qwen",
)

model.eval()
video_path = "./examples/video1.mp4"
qs = "Describe this video in detail"

vr = VideoReader(video_path, ctx=cpu(0), num_threads=1)
fps = float(vr.get_avg_fps())
frame_indices = np.array([i for i in range(0, len(vr), round(fps),)])
video = []
for frame_index in frame_indices:
    img = vr[frame_index].asnumpy()
    video.append(img)
video = np.stack(video)
image_sizes = [video[0].shape[:2]]
video = process_images(video, image_processor, model.config)
video = [item.unsqueeze(0) for item in video]

qs = DEFAULT_IMAGE_TOKEN + "\n" + qs
conv = conv_templates["qwen"].copy()
conv.append_message(conv.roles[0], qs)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()

input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(model.device)
stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)
with torch.inference_mode():
    output_ids = model.generate(
        input_ids,
        images=video,
        image_sizes=image_sizes,
        do_sample=False,
        temperature=0.2,
        max_new_tokens=128,
        use_cache=True,
        stopping_criteria=[stopping_criteria],
    )
pred = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()