Upload 4 files

bias.md

@@ -0,0 +1,13 @@
+| Field | Response |
+|:---|:---|
+| Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | None |
+| Bias Metric (If Measured): | [BBQ Accuracy Scores in Ambiguous Contexts](https://github.com/nyu-mll/BBQ/) |
+| Which characteristic (feature) show(s) the greatest difference in performance?: | The model shows high variance across many characteristics when used at a high temperature, with the greatest measurable difference seen in categories such as Gender Identity and Race x Gender. |
+| Which feature(s) have the worst performance overall? | Age (ambiguous) has both the lowest category accuracy listed (0.75) and a notably negative bias score (–0.56), indicating it is the worst-performing feature overall in this evaluation. |
+| Measures taken to mitigate against unwanted bias: | None |
+| If using internal data, description of methods implemented in data acquisition or processing, if any, to address the prevalence of identifiable biases in the training, testing, and validation data: | The training datasets contain a large amount of synthetic data generated by LLMs. We manually curated prompts. |
+| Tools used to assess statistical imbalances and highlight patterns that may introduce bias into AI models: | Bias Benchmark for Question Answering (BBQ) |
+| Tools used to assess statistical imbalances and highlight patterns that may introduce bias into AI models: | The datasets, which include video datasets (e.g., YouCook2, VCG Human Dataset) and image captioning datasets, do not collectively or exhaustively represent all demographic groups (and proportionally therein).
+For instance, these datasets do not contain explicit mentions of demographic classes such as age, gender, or ethnicity in over 80% of samples. In the subset where analysis was performed, certain datasets contain skews in the representation of participants—for example, perceived gender of "female" participants may be significant compared to "male" participants for certain datasets. Separately, individuals aged "40 to 49 years" and “20 to 29 years” are the most frequent among ethnic identifiers. Toxicity analysis was additionally performed on several datasets to identify potential not-safe-for-work samples and risks.
+To mitigate these imbalances, we recommend considering evaluation techniques such as bias audits, fine-tuning with demographically balanced datasets, and mitigation strategies like counterfactual data augmentation to align with the desired model behavior. This evaluation was conducted on a data subset ranging from 200 to 3,000 samples per dataset; as such, certain limitations may exist in the reliability of the embeddings. A baseline of 200 samples was used across all datasets, with larger subsets of up to 3,000 samples utilized for certain in-depth analyses.
+ |

explainability.md

@@ -0,0 +1,15 @@
+Field                                                                                                  |  Response
+:------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------
+Intended Task/Domain:                                                                   |  Visual Question Answering
+Model Type:                                                                                            |  Transformer
+Intended Users:                                                                                        | Individuals and businesses that need to process documents such as invoices, receipts, and manuals. Also, users who are building multi-modal agents and RAG systems.
+Output:                                                                                                |  Text 
+ Tools used to evaluate datasets to identify synthetic data and ensure data authenticity. | We used a Gemma-3 4B-based filtering model fine-tuned on [Nemotron Content Safety Dataset v2](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0) to ensure the quality of synthetic data.
+Describe how the model works:                                                                          | Vision Encoder and a Nemotron 5.5H -12B Language Encoder. It processes multiple input modalities, including text, multiple images, and video. It fuses these inputs and uses its large language model backbone with a 128K context length to perform visual Q&A, summarization, and data extraction.
+Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of:  |  Not Applicable
+Technical Limitations & Mitigation:                                                                    |  The model has a limited maximum resolution determined by a 12-tile layout constraint, where each tile is 512x512 pixels. It also supports a limited number of input images (up to 4) and has a maximum context length of 128K tokens for combined input and output.
+Verified to have met prescribed NVIDIA quality standards:  |  Yes
+Performance Metrics:                                                                                   |  Accuracy (Visual Question Answering), Latency, Throughput
+Potential Known Risks:                                                                                 | The Model may produce output that is biased, toxic, or incorrect responses. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts. The Model may also generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text, producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.While we have taken safety and security into account and are continuously improving, outputs may still contain political content, misleading information, or unwanted bias beyond our control.
+Licensing:                                                                                             |  Governing Terms: Use of this model is governed by the [ NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/)
+

privacy.md

@@ -0,0 +1,13 @@
+Field                                                                                                                              |  Response
+:----------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------
+Generatable or reverse engineerable personal data?                                                     |  No
+Personal data used to create this model?                                                                                       |  No
+Was consent obtained for any personal data used?                                                                                             |  Not Applicable
+A description of any methods implemented in data acquisition or processing, if any, to address the prevalence of personal data in the training data, where relevant and applicable. | We used only prompts that do not contain any personal data for synthetic data generation. 
+How often is dataset reviewed?                                                                                                     |  Before release and during dataset creation and model training <br><br>
+Is there provenance for all datasets used in training?                                                                                |  Yes
+Does data labeling (annotation, metadata) comply with privacy laws?                                                                |  Yes
+Is data compliant with data subject requests for data correction or removal, if such a request was made?                           |  No, not possible with externally-sourced data.
+Applicable Privacy Policy        | [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/)
+During AI model development, strict adherence to copyright policy ensured compliance through risk mitigation and legal reviews. Post-data collection, reserved rights content is identified and removed, with verified opt-out processes for rightsholders. Detailed records document due diligence and transparency.
+We employ automated tools and data processing techniques to scan for Personally Identifiable Information (PII) during pre-training to identify and filter certain categories of personal information, including public-facing contact details such as email addresses and phone numbers. Scans of Common Crawl, CC-News, and Wikimedia datasets did not detect PII in the majority of samples. However, Microsoft Presidio indicated potential findings including business contact information embedded in natural language, such as email addresses and phone numbers. These were removed using verified instances of PII through a combination of automated filtering and human-in-the-loop validation.

safety.md

@@ -0,0 +1,10 @@
+Field                                               |  Response
+:---------------------------------------------------|:----------------------------------
+Model Application Field(s):                               |  Customer Service, Media & Entertainment, Enterprise Document Intelligence and Processing & Retail 
+Describe the life critical impact (if present).   |  Not Applicable 
+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: | We used a guard model for content safety to exclude potentially harmful data from  training. 
+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) | We used a Gemma-3 4B-based guard model trained on [Nemotron Content Safety Dataset v2](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0) for content safety to exclude potentially illegal or harmful content from the training. We also did CSAM checks on our image datasets for training.
+Use Case Restrictions:                              |  Use of this model is governed by the [ NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/)
+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.
+This AI model was developed based on our policies to ensure responsible data handling and risk mitigation. The datasets used for training have been scanned for harmful content and illegal content, consistent with our policies including scanning for Child Sexual Abuse Material (CSAM). Ongoing review and monitoring mechanisms are in place based on our policies and to maintain data integrity.
+The model was optimized explicitly for instruction following and as such is more susceptible to prompt injection and jailbreaking in various forms as a result of its instruction tuning. This means that the model should be paired with additional rails or system filtering to limit exposure to instructions from malicious sources -- either directly or indirectly by retrieval (e.g. via visiting a website) -- as they may yield outputs that can lead to harmful, system-level outcomes up to and including remote code execution in agentic systems when effective security controls including guardrails are not in place. The model may generate answers that may be inaccurate, omit key information, include irrelevant or redundant text, or produce socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.