NVIDIA Nemotron-Parse v2.0 - document understanding VLM: image in, structured text (with bboxes and semantic classes) out.
Safety
| Field | Response |
|---|---|
| Model Application Field(s): | Document intelligence, information retrieval, enterprise automation, data extraction, multimodal data curation, and retrieval-augmented generation workflows. |
| Describe the life critical impact (if present). | Not Applicable. This model is not intended to make life-critical, legal, medical, financial, or safety-critical decisions without downstream validation and human oversight. |
| (For GPAI Models): Description of methods implemented in data acquisition or processing, if any, to address other types of potentially harmful data in the training, testing, and validation data: | Dataset curation, filtering, provenance tracking, and review are applied where applicable to reduce harmful or inappropriate content exposure. |
| (For GPAI Models): Description of any methods implemented in data acquisition or processing, if any, to address illegal or harmful content in the training data, including, but not limited to, child sexual abuse material (CSAM) and non-consensual intimate imagery (NCII) | Dataset handling follows NVIDIA data governance and safety review processes. The model is intended for document parsing and is not designed to generate illegal or harmful content. |
| Use Case Restrictions: | Use of this model must comply with the NVIDIA Open Model License Agreement. Users are responsible for ensuring they have rights and permissions for input documents and images. |
| Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to. |
(For GPAI Models): This AI model was developed based on our policies to ensure responsible data handling and risk mitigation. The datasets used for training have been reviewed for harmful content and illegal content consistent with our policies. Ongoing review and monitoring mechanisms are in place based on our policies and to maintain data integrity. NVIDIA Nemotron Parse 2.0 is intended for document extraction and structure parsing. Developers are responsible for safe system integration, input-data permissions, output validation, and use-case-specific controls.
You are responsible for ensuring that your use of NVIDIA-provided models complies with all applicable laws.