Task
Image To Text
G
unsloth/GLM-OCR
Image To Text·unsloth· 28.0K· 34
GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task reinforcement learning to improve training efficiency, recognition accuracy, and generalization. The model integrates the CogViT visual encoder pre-trained on large-scale image–text data, a lightweight cross-moda
# pull & run locally
pip install mlforge-sdk && mlforge pull unsloth/GLM-OCR
pip install mlforge-sdk && mlforge pull unsloth/GLM-OCR
Model details
Provider
unsloth
Framework
transformers
Size
2.5 GB
License
mit
Downloads
28.0K
Likes
34
Updated
2026-02-03
About unsloth/GLM-OCR
GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task reinforcement learning to improve training efficiency, recognition accuracy, and generalization. The model integrates the CogViT visual encoder pre-trained on large-scale image–text data, a lightweight cross-modal connector with efficient token downsampling, and a GLM-0.5B language decoder. Combined with a two-stage pipeline of layout analysis and parallel recognition based on PP-DocLayout-V3, GLM-OCR delivers robust and high-quality OCR performance across diverse document layouts.