Subscription required to access this content
Model
Generates responses for roleplaying, retrieval augmented generation, and function calling with vision understanding and reasoning capabilities.
Subscription required to access this content
| Field | Response |
|---|---|
| Intended Application(s) & Domain(s): | Visual Question Answering. |
| Model Type: | Vision Language Model |
| Intended Users: | The primary intended users of the model are practitioners and researchers in computer vision, natural language processing, machine learning, and artificial intelligence. |
| Output: | Text |
| Describe how the model works: | Chat based on image content. Chat for roleplaying, retrieval augmented generation, and function calling. |
| Technical Limitations: | This model may not perform well on domain specific images. |
| Known Risk: | 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. |
| Verified to have met prescribed NVIDIA standards: | Yes |
| Performance Metrics: | Visual Question Answering (VQA), GQA, MMBench-en, MMMU, SQA-Image, etc. Text based evaluations include Automatic Evaluation - Commonsense Reasoning & Language Understanding, Automatic Evaluation - Open LLM Leaderboard, Instruction Following, Berkeley Function Calling, and ChatRAG-Bench. |
| Potential Known Risks: | None Known |
| Licensing: | NVIDIA AI Foundation Models Community License |