loay/English-Scanned-Document-OCR-LFM2.5-VL-450M-LoRA-Experimental
English-Scanned-Document-OCR-LFM2.5-VL-450M-LoRA-Experimental
This repository contains a LoRA adapter fine-tuned from LiquidAI/LFM2.5-VL-450M for English scanned/printed document OCR experiments.
The run was trained primarily for full-page transcription on synthetic and synthetic-style document data, with emphasis on scanned pages, dense text, reading order, and degraded print-like inputs.
This model is being published as an experiment record, not as a production OCR release.
What It Was Trained For
- English scanned and printed document OCR
- Full-page transcription
- Reading-order preservation
- Dense text and long-page OCR
- Some degraded/noisy document cases
What It Is Not
- Not a general-purpose OCR model
- Not validated as a robust out-of-domain document parser
- Not reliable for broad real-world generalization
- Not intended for handwriting, multilingual OCR, or production deployment without further validation
Training Summary
This adapter was fine-tuned from LiquidAI/LFM2.5-VL-450M.
Internal held-out evaluation showed improvements on some in-domain slices, especially long and noisy scanned-page transcription, but the gains did not scale consistently across broader distributions and did not demonstrate strong generalization.
Evaluation Notes
Results reported for this experiment should be interpreted as in-domain / internal evaluation only.
Key limitations:
- performance is sensitive to dataset distribution
- generalization outside the training-style data is limited
- behavior can be unstable across layout types
- benchmark transfer does not support claiming broad OCR capability
Intended Use
This repository is intended for:
- experiment tracking
- reproducibility
- adapter reuse for further OCR research on top of LFM2.5-VL-450M
It is not intended as a general end-user OCR checkpoint.
License
The upstream base model is released under the LFM Open License v1.0. Use of this adapter must comply with the base model license and its terms.
