Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- onnx
|
| 5 |
+
- ocr
|
| 6 |
+
- vision-language
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# GLM-OCR ONNX Models
|
| 10 |
+
|
| 11 |
+
ONNX exports of [zai-org/GLM-OCR](https://huggingface.co/zai-org/GLM-OCR) for use with [ORT](https://onnxruntime.ai/) in the `papers-extract` pipeline.
|
| 12 |
+
|
| 13 |
+
## Attribution
|
| 14 |
+
|
| 15 |
+
The original GLM-OCR model was created by [zai-org](https://huggingface.co/zai-org) and is released under the **MIT License**.
|
| 16 |
+
|
| 17 |
+
These ONNX files are derived from the original weights with attention fusion optimizations (GQA/MHA surgery) for efficient CUDA inference. See the original model card at [zai-org/GLM-OCR](https://huggingface.co/zai-org/GLM-OCR) for full details.
|
| 18 |
+
|
| 19 |
+
## License
|
| 20 |
+
|
| 21 |
+
MIT License - see [LICENSE](LICENSE) for details.
|