This is the OpenVINO accelerated version for GOT-OCR2.0. To use this model, download all files from the origin repo stepfun-ai/GOT-OCR2_0 and copy everything to the weight folder. The file structure should look like this:
.
│ app.py
│ convert_model.py
├─weight
│ config.json
│ generation_config.json
│ got_vision_b.py
│ modeling_GOT.py
│ openvino_language_model.bin
│ openvino_language_model.xml
│ openvino_text_embeddings_model.bin
│ openvino_text_embeddings_model.xml
│ openvino_vision_embeddings_merger_model.bin
│ openvino_vision_embeddings_merger_model.xml
│ openvino_vision_embeddings_model.bin
│ openvino_vision_embeddings_model.xml
│ qwen.tiktoken
│ render_tools.py
│ special_tokens_map.json
│ tokenization_qwen.json
│ tokenizer_config.json
Libraries require:
pip install "openvino" "torch" "transformers" "torchvision" "Pillow" "nncf" "requests" "numpy"
Simply running the following command
python app.py --image-file /path/to/image
For more instruction, refer to GitHub Page
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for can-gaa-hou/GOT-OCR2.0-OpenVINO-INT4
Base model
stepfun-ai/GOT-OCR2_0