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

numind
/
NuMarkdown-8B-Thinking

Image-to-Text
Transformers
Safetensors
qwen2_5_vl
image-text-to-text
OCR
vision-language
VLM
Reasoning
document-to-markdown
qwen2.5
markdown
extraction
RAG
text-generation-inference
Model card Files Files and versions
xet
Community
8

Instructions to use numind/NuMarkdown-8B-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use numind/NuMarkdown-8B-Thinking with Transformers:

    # Use a pipeline as a high-level helper
    # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5.
    # You must load the model directly (see below) or downgrade to v4.x with:
    # 'pip install "transformers<5.0.0'
    from transformers import pipeline
    
    pipe = pipeline("image-to-text", model="numind/NuMarkdown-8B-Thinking")
    # Load model directly
    from transformers import AutoProcessor, AutoModelForImageTextToText
    
    processor = AutoProcessor.from_pretrained("numind/NuMarkdown-8B-Thinking")
    model = AutoModelForImageTextToText.from_pretrained("numind/NuMarkdown-8B-Thinking")
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

πŸ“‹ Documentation Enhancement Suggestion

#8 opened 3 months ago by
CroviaTrust

What about multi page pdfs

1
#7 opened 4 months ago by
aniket2025

Quantizations version

#5 opened 9 months ago by
baiall

NuMarkdown-8B-reasoning on A100 40GB is extremely slow (even for 1 token)

πŸ‘ 1
2
#4 opened 9 months ago by
Fedoration

This is so exciting!

🀝 5
1
#2 opened 10 months ago by
ashercn97
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs