nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1

Note

This is a remotely-sourced model from the Nemotron_Nano_VL plugin, maintained by the community. It is not part of FiftyOne core and may have special installation requirements. Please review the plugin documentation and license before use.

Llama Nemotron Nano VL is a leading document intelligence vision language model (VLMs) that enables the ability to query and summarize images from the physical or virtual world..

Details

• Model name: nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1

• Model source: https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1

• Model author: NVIDIA

• Model license: NVIDIA Open License Agreement

• Exposes embeddings? no

• Tags: detection, ocr, VLM, classification, zero-shot, visual-agent

Requirements

• Packages: huggingface-hub, transformers, torch, torchvision, timm, einops, open-clip-torch

• CPU support

  • yes

• GPU support

  • yes

Example usage

import fiftyone as fo
import fiftyone.zoo as foz

foz.register_zoo_model_source("https://github.com/harpreetsahota204/Nemotron_Nano_VL")

dataset = foz.load_zoo_dataset(
    "coco-2017",
    split="validation",
    dataset_name=fo.get_default_dataset_name(),
    max_samples=50,
    shuffle=True,
)

model = foz.load_zoo_model("nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1")

dataset.apply_model(model, label_field="predictions")

session = fo.launch_app(dataset)