|
il y a 1 semaine | |
---|---|---|
.. | ||
.gitattributes | il y a 1 semaine | |
README.md | il y a 1 semaine | |
added_tokens.json | il y a 1 semaine | |
chat_template.json | il y a 1 semaine | |
config.json | il y a 1 semaine | |
generation_config.json | il y a 1 semaine | |
model.safetensors | il y a 1 semaine | |
preprocessor_config.json | il y a 1 semaine | |
processor_config.json | il y a 1 semaine | |
special_tokens_map.json | il y a 1 semaine | |
tokenizer.json | il y a 1 semaine | |
tokenizer_config.json | il y a 1 semaine | |
vocab.json | il y a 1 semaine |
license: cdla-permissive-2.0 datasets:
The Code Formula Model processes an image of a code snippet or formula at 120 DPI and outputs its content.
Code Snippets:
The model identifies the programming language and outputs the code repsecting the indendation shown in the given image. The output format will be:
"<_<programming language>_> <content of the image>"
Example:
"<Java> System.out.println("Hello World.");"
Formulas:
The model generates the corresponding LaTeX code.
This model was trained using the following two datasets:
@techreport{Docling,
author = {Deep Search Team},
month = {8},
title = {{Docling Technical Report}},
url={https://arxiv.org/abs/2408.09869},
eprint={2408.09869},
doi = "10.48550/arXiv.2408.09869",
version = {1.0.0},
year = {2024}
}
@article{nassar2025smoldocling,
title={SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion},
author={Nassar, Ahmed and Marafioti, Andres and Omenetti, Matteo and Lysak, Maksym and Livathinos, Nikolaos and Auer, Christoph and Morin, Lucas and de Lima, Rafael Teixeira and Kim, Yusik and Gurbuz, A Said and others},
journal={arXiv preprint arXiv:2503.11576},
year={2025}
}