Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

commandeaw
/
DW-KhotTaeVL-2B-QueryFrames

Video-Text-to-Text
Transformers
English
video
video-question-answering
multimodal
vision-language
qwen3-vl
inference-time
frame-selection
clip
Model card Files Files and versions
xet
Community

Instructions to use commandeaw/DW-KhotTaeVL-2B-QueryFrames with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use commandeaw/DW-KhotTaeVL-2B-QueryFrames with Transformers:

    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("commandeaw/DW-KhotTaeVL-2B-QueryFrames", dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
DW-KhotTaeVL-2B-QueryFrames
43.3 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 10 commits
commandeaw's picture
commandeaw
Add scope section: full Video-MME mini 2700Q result (+0.22 pp)
d0f5738 verified 6 days ago
  • .gitattributes
    1.52 kB
    initial commit 7 days ago
  • LICENSE
    751 Bytes
    Initial release: DW-KhotTaeVL-2B-QueryFrames v1.0 7 days ago
  • NOTICE
    1.11 kB
    Initial release: DW-KhotTaeVL-2B-QueryFrames v1.0 7 days ago
  • README.md
    12.1 kB
    Add scope section: full Video-MME mini 2700Q result (+0.22 pp) 6 days ago
  • build_hybrid.py
    6.46 kB
    Initial release: DW-KhotTaeVL-2B-QueryFrames v1.0 7 days ago
  • dw_queryframes.py
    8.84 kB
    Fix transformers 5.x API change: get_text_features now returns BaseModelOutputWithPooling 7 days ago
  • eval_videomme.py
    10.5 kB
    Add --start-idx for chunked evaluation (MPS resilience) 7 days ago
  • example_usage.py
    1.99 kB
    example_usage: rename Wild-mode → MCQ-mode terminology 7 days ago