ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
VITA
Model
NVIDIA
NVIDIA
VITA

VITA Visual Language Model

This model is backed by NVIDIA's Plus Plus (++) Promise
to learn more about the quality of the datasets used to train this model.
FieldResponse
Intended Application(s) & Domain(s):Video QnA and temporal localization for factory and industrial use cases.
Model Type:Vision Language Model
Intended Users:This model is intended for developers building Vision based monitoring solutions
Output:Text
Describe how the model works:Encodes image and mapped to text representation. Passes this through LLM to generate a response
Technical Limitations:Model may sometimes generate incorrect and faulty timestamps
Verified to have met prescribed NVIDIA standards:Yes
Performance Metrics:Video ChatGPT and Video QA
Licensing:licenses.