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, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("numind/NuMarkdown-8B-Thinking") model = AutoModelForMultimodalLM.from_pretrained("numind/NuMarkdown-8B-Thinking", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -27,7 +27,7 @@ pipeline_tag: text-generation
|
|
| 27 |
|
| 28 |
---
|
| 29 |
|
| 30 |
-
# Reasoning comes to OCR
|
| 31 |
|
| 32 |
**NuMarkdown-8B-Thinking** is the first reasoning OCR VLM. It is specifically trained to convert documents into clean GitHub-flavoured Markdown. It generates thoughts tokens to figure out the layout of the document before generating the Markdown file.
|
| 33 |
It is particularly good at understanding documents with weird layouts and complex tables. The number of thinking tokens can vary from 20% to 500% of the final answer, depending on the task difficulty.
|
|
|
|
| 27 |
|
| 28 |
---
|
| 29 |
|
| 30 |
+
# Reasoning comes to OCR 🧠✨📄🤘
|
| 31 |
|
| 32 |
**NuMarkdown-8B-Thinking** is the first reasoning OCR VLM. It is specifically trained to convert documents into clean GitHub-flavoured Markdown. It generates thoughts tokens to figure out the layout of the document before generating the Markdown file.
|
| 33 |
It is particularly good at understanding documents with weird layouts and complex tables. The number of thinking tokens can vary from 20% to 500% of the final answer, depending on the task difficulty.
|