Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

MCG-NJU
/
TimeLens2-4B

Video-Text-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
video
temporal-grounding
qwen3-vl
Model card Files Files and versions
xet
Community

Instructions to use MCG-NJU/TimeLens2-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use MCG-NJU/TimeLens2-4B with Transformers:

    # Load model directly
    from transformers import AutoProcessor, AutoModelForMultimodalLM
    
    processor = AutoProcessor.from_pretrained("MCG-NJU/TimeLens2-4B")
    model = AutoModelForMultimodalLM.from_pretrained("MCG-NJU/TimeLens2-4B", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
TimeLens2-4B / assets
413 kB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 9 commits
ZhuYuhan's picture
ZhuYuhan
Clarify TimeLens-Bench re-annotations
8df5c62 verified 25 days ago
  • benchmark_results.png
    323 kB
    xet
    Clarify TimeLens-Bench re-annotations 25 days ago
  • benchmark_results.svg
    89.3 kB
    Clarify TimeLens-Bench re-annotations 25 days ago