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
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
What about multi page pdfs
#7
by aniket2025 - opened
If i have multi page pdfs, then how can i give those pdfs as input and get per page markdown result or combined result?
Hi @aniket2025 . You can try to send the entire document to NuMarkdown. If the context is too small (32k), I would suggest that you split the document into pages and send each one of them to NuMarkdown.