Image-to-Text
Transformers
Safetensors
English
idefics3
image-text-to-text
chemistry
ocr
chemical-structure
document-understanding
vision-language-model
patent-analysis
smoldocling
Instructions to use docling-project/ChemicalOCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use docling-project/ChemicalOCR 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/ChemicalOCR")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("docling-project/ChemicalOCR") model = AutoModelForMultimodalLM.from_pretrained("docling-project/ChemicalOCR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- fbfc72c722eb1473bab72d6646d644df6d9120e9d555bcbb68675756a3e37c48
- Size of remote file:
- 1.03 GB
- SHA256:
- 040ce3dcbb094895417390f593860e69d6c09f08405e3fd6e6e0af160226eb42
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.