[フレーム]

lucataco/moondream2

moondream2 is a small vision language model designed to run efficiently on edge devices

Public
6.4M runs
Playground API Examples README Versions

Run time and cost

This model costs approximately 0ドル.0015 to run on Replicate, or 666 runs per 1,ドル but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 2 seconds.

Readme

Moondream2

moondream2 is a small vision language model designed to run efficiently on edge devices. Check out the GitHub repository for details, or try it out on the Hugging Face Space!

Benchmarks

Release VQAv2 GQA TextVQA DocVQA TallyQA
(simple/full)
POPE
(rand/pop/adv)
2024年07月23日 (latest) 79.4 64.9 60.2 61.9 82.0 / 76.8 91.3 / 89.7 / 86.9
2024年05月20日 79.4 63.1 57.2 30.5 82.1 / 76.6 91.5 / 89.6 / 86.2
2024年05月08日 79.0 62.7 53.1 30.5 81.6 / 76.1 90.6 / 88.3 / 85.0
2024年04月02日 77.7 61.7 49.7 24.3 80.1 / 74.2 -
2024年03月13日 76.8 60.6 46.4 22.2 79.6 / 73.3 -
2024年03月06日 75.4 59.8 43.1 20.9 79.5 / 73.2 -
2024年03月04日 74.2 58.5 36.4 - - -

Usage

The model is updated regularly, so we recommend pinning the model version to a specific release as shown above.

Model created

AltStyle によって変換されたページ (->オリジナル) /