Software Mansion 发布 React Native ExecuTorch 版 CLIP 图像编码器
原标题：software-mansion/react-native-executorch-clip-vit-base-patch32
AI 摘要
软件公司 Software Mansion 在 Hugging Face 上发布了用于 React Native ExecuTorch 库的 CLIP ViT-B/32 图像编码器模型，以 .pte 格式提供，支持 xnnpack 后端。该模型基于 OpenAI 的 clip-vit-base-patch32，导出时使用 ExecuTorch 1.1.0，不保证向前兼容。开发者可在 React Native 应用中集成该模型进行图像编码，或参考官方文档在其他 ExecuTorch 运行时中使用。
正文节选
--- license: mit --- # Introduction This repository hosts the image encoder of [clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) model for the [React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It includes the model exported for xnnpack in `.pte` format, ready for use in the **ExecuTorch** runtime. If you'd like to run these models in your own ExecuTorch runtime, refer to the [official documentation](https://pytorch.org/executo