Image-to-Text
Transformers
PyTorch
English
udop
text-generation
chemistry
markush
cxsmiles
molecular-structure
ocr
document-understanding
vision-language-model
patent-analysis
Instructions to use docling-project/MarkushGrapher-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use docling-project/MarkushGrapher-2 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="docling-project/MarkushGrapher-2")# Load model directly from transformers import AutoProcessor, AutoModelForSeq2SeqLM processor = AutoProcessor.from_pretrained("docling-project/MarkushGrapher-2") model = AutoModelForSeq2SeqLM.from_pretrained("docling-project/MarkushGrapher-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- d592851d3785fb43996b1ff91585cf4912a58c6e22e46714e776dac767e4210a
- Size of remote file:
- 4.54 kB
- SHA256:
- 97f8b6143a3f898ee031aeb460acd5586aef220794d9ad73b5cd366bc37b897d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.