Moondream

Moondream detects objects, returns points and answers image questions.

任务: detection, point detection
尺寸: 2, 3 at 384 to 512 px
安装: pip install "libreyolo[vlm]"
支持层级: 兄弟层级，自 v1.6.0 起。一个独立的产品面，有自己的工厂和契约。
许可: 代码采用 MIT，权重采用 Apache-2.0 (2); BSL 1.1 (3)。商用

Install

bash

pip install "libreyolo[vlm]"

Predict

Python

from libreyolo import LibreVLM, SAMPLE_IMAGE model = LibreVLM("moondream-2", device="cpu")model.set_classes(["person", "building"])result = model(SAMPLE_IMAGE)print(result.boxes)

The default selects Moondream 2. moondream-3 names the BSL 1.1 Moondream 3 model, but it does not load in 1.6.0: the LibreYOLO/LibreMoondream3 mirror is missing weight shards. Use task="point" for points and chat() for native text responses. Training is not supported.

Licensing

请检查你所下载的具体权重在 Hugging Face 仓库中的许可。LibreYOLO 组织里的每个检查点都附有许可，同一家族内也不一定相同。该仓库是权威来源；以下摘要说明本页上次验证时适用的情况。

这里只说明涉及的许可证，不构成法律意见。如果答案对商用很重要，请自行阅读许可证并咨询法律顾问。

原始工作: Moondream, Moondream
上游许可: Apache-2.0 (2); BSL 1.1 (3)
上游来源: huggingface.co/moondream
LibreYOLO 代码: MIT
权重: 采用 Apache-2.0 (2); BSL 1.1 (3) 许可，重新发布在 huggingface.co/LibreYOLO
解读: Moondream 2 uses Apache-2.0. Moondream 3 uses BSL 1.1 with the publisher's additional-use conditions; it is not an unrestricted Apache-2.0 checkpoint.