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
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

NemoStation
/
Marlin-2B

Video-Text-to-Text
Transformers
Safetensors
English
qwen3_5
text-generation
video
multimodal
video-captioning
temporal-grounding
qwen
VLM
custom_code
Model card Files Files and versions
xet
Community
3

Instructions to use NemoStation/Marlin-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use NemoStation/Marlin-2B with Transformers:

    # Load model directly
    from transformers import AutoProcessor, AutoModelForCausalLM
    
    processor = AutoProcessor.from_pretrained("NemoStation/Marlin-2B", trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained("NemoStation/Marlin-2B", trust_remote_code=True)
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Question about the evaluation metrics for captioning benchmarks

#3 opened 1 day ago by
ygyjrc
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs