XiaomiMiMo/MiMo-VL-7B-SFT

Note

This is a remotely-sourced model from the MiMo_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.

MiMo-VL-7B is a compact yet powerful vision-language model developed through extensive pre-training and reinforcement learning to achieve state-of-the-art performance on a variety of visual-language tasks..

Details

• Model name: XiaomiMiMo/MiMo-VL-7B-SFT

• Model source: https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-SFT

• Model author: XiaomiMiMo

• Model license: MIT

• Exposes embeddings? no

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

Requirements

• Packages: huggingface-hub, transformers, torch, torchvision, qwen-vl-utils, accelerate

• 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/MiMo_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("XiaomiMiMo/MiMo-VL-7B-SFT")

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

session = fo.launch_app(dataset)