This model is a fine-tuned version of Qwen/Qwen2.5-VL-7B-Instruct.
The base model is released under the Apache License 2.0.
This fine-tuned model is also released under the Apache License 2.0.
Training data: https://zenodo.org/records/18597235.
To adapt OCR models to the typographic and material characteristics of 18th-century printed texts. This design balances transcription fidelity, historical diversity, and scalability while preserving historically meaningful orthographic variation.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support