| --- |
| license: mit |
| --- |
| |
| > [!IMPORTANT] |
| > This is a copy of the model weights from the [https://huggingface.co/rednote-hilab/dots.ocr](https://huggingface.co/rednote-hilab/dots.ocr) model. These weights cannot be used for other purposes. If you wish to do so, please visit the original model page. |
|
|
| Previously, inference with the model [[https://huggingface.co/rednote-hilab/dots.ocr](https://huggingface.co/rednote-hilab/dots.ocr)] would fail with the following error: |
| **Error loading dots-ocr model: Received a NoneType for argument 'video_processor', but a BaseVideoProcessor was expected.** in the latest Transformers versions. |
| |
| This page, which includes the model weights and corrected configuration, fixed the issue and allowed Transformers inference to run smoothly. |
| |
| > [!note] |
| Last updated: 4:00 AM (IST), October 25, 2025. |
| |
| > [!note] |
| The latest transformers version used as of the above date is `transformers==4.57.1` and the torch version `2.8.0+cu126` |
| |
| ## Quick Start with Transformers |
| |
| > #### Install the required packages |
| |
| ```py |
| !pip install transformers torch torchvision gradio hf_xet \ |
| huggingface_hub pillow accelerate peft \ |
| matplotlib requests einops av sentencepiece\ |
| transformers-stream-generator |
| ``` |
| |
| > ### notebook login |
| |
| ```py |
| from huggingface_hub import notebook_login, HfApi |
| notebook_login() |
| ``` |
| |
| > ### Run [app.py] |
