React Native ExecuTorch 发布 LLaMa 3.2 量化模型
原标题：software-mansion/react-native-executorch-llama-3.2
AI 摘要
software-mansion 在 Hugging Face 上发布了用于 React Native ExecuTorch 库的 LLaMa 3.2 模型仓库，包含 1B 和 3B 版本及其量化版本（.pte 格式），并提供了 QLoRa、SpinQuant 等优化版本。这些模型使用 ExecuTorch v0.6.0 导出，不保证向前兼容，用户需确保运行时兼容。官方推荐使用 QLoRa 版本以获得最佳性能与质量平衡。
正文节选
--- license: llama3.2 pipeline_tag: text-generation tags: - executorch library_name: executorch --- # Introduction This repository hosts the **LLaMa 3.2** models for the [React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It includes both the **1B** and **3B** versions of the LLaMa model, as well as their **quantized** versions in `.pte` format, ready for use in the **ExecuTorch** runtime. If you'd like to run these models in your own ExecuTorch runtime,