Update README.md
Browse files
README.md
CHANGED
|
@@ -417,7 +417,7 @@ Please report security vulnerabilities or NVIDIA AI Concerns [here](https://app.
|
|
| 417 |
| Verified to have met prescribed NVIDIA quality standards: | Yes |
|
| 418 |
| Performance Metrics: | Accuracy (e.g., character error rate), throughput, and latency. |
|
| 419 |
| Potential Known Risks: | The model may not always extract or transcribe all text with perfect accuracy, particularly in cases of poor image quality or highly stylized fonts. |
|
| 420 |
-
| Licensing & Terms of Use: |
|
| 421 |
|
| 422 |
|
| 423 |
## Privacy
|
|
@@ -440,6 +440,6 @@ Please report security vulnerabilities or NVIDIA AI Concerns [here](https://app.
|
|
| 440 |
| Field | Response |
|
| 441 |
| ----- | ----- |
|
| 442 |
| Model Application Field(s): | Text recognition and structured OCR for multimodal retrieval. Inputs can include natural scene images, scanned documents, charts, tables, and infographics. |
|
| 443 |
-
| Use Case Restrictions: |
|
| 444 |
| Model and dataset restrictions: | The principle of least privilege (PoLP) is applied, limiting access for dataset generation and model development. Restrictions enforce dataset access only during training, and all dataset license constraints are adhered to. |
|
| 445 |
| Describe the life critical impact (if present): | Not applicable. |
|
|
|
|
| 417 |
| Verified to have met prescribed NVIDIA quality standards: | Yes |
|
| 418 |
| Performance Metrics: | Accuracy (e.g., character error rate), throughput, and latency. |
|
| 419 |
| Potential Known Risks: | The model may not always extract or transcribe all text with perfect accuracy, particularly in cases of poor image quality or highly stylized fonts. |
|
| 420 |
+
| Licensing & Terms of Use: | The model is governed by the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information:[Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) |
|
| 421 |
|
| 422 |
|
| 423 |
## Privacy
|
|
|
|
| 440 |
| Field | Response |
|
| 441 |
| ----- | ----- |
|
| 442 |
| Model Application Field(s): | Text recognition and structured OCR for multimodal retrieval. Inputs can include natural scene images, scanned documents, charts, tables, and infographics. |
|
| 443 |
+
| Use Case Restrictions: | The model is governed by the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information:[Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) |
|
| 444 |
| Model and dataset restrictions: | The principle of least privilege (PoLP) is applied, limiting access for dataset generation and model development. Restrictions enforce dataset access only during training, and all dataset license constraints are adhered to. |
|
| 445 |
| Describe the life critical impact (if present): | Not applicable. |
|