diff --git a/README.md b/README.md index e70a56e..2316c33 100644 --- a/README.md +++ b/README.md @@ -1799,6 +1799,23 @@ ollama run jingyaogong/minimind2 # 其他可选 minimind2-r1 / minimind2-small / 我是一个语言模型... ``` +## [MNN](https://github.com/alibaba/MNN) + +MNN是面向端侧的AI推理引擎,支持多种开源LLM模型推理,轻量化、高性能。 + +1. 模型转换 +``` +cd MNN/transformers/llm/export +# 导出4bit HQQ量化的MNN模型 +python llmexport.py --path /path/to/MiniMind2/ --export mnn --hqq --dst_path MiniMind2-MNN +``` + +2. 在Mac或手机上测试 +``` +./llm_demo /path/to/MiniMind2-MNN/config.json prompt.txt +``` +或者下载APP测试 + > 以上三方框架的更多用法请参考对应官方文档😊 # 📌 Acknowledge diff --git a/README_en.md b/README_en.md index f8ea2a2..d4e2d3d 100644 --- a/README_en.md +++ b/README_en.md @@ -1728,6 +1728,23 @@ ollama run jingyaogong/minimind2 # Other options: minimind2-r1 / minimind2-small I am a language model... ``` +## [MNN](https://github.com/alibaba/MNN) + +MNN is a lightweight, high-performance AI inference engine for on-device applications, supporting inference for various open-source LLM models. + +1. **Model Conversion** + ``` + cd MNN/transformers/llm/export + # Export the 4-bit HQQ quantized MNN model + python llmexport.py --path /path/to/MiniMind2/ --export mnn --hqq --dst_path MiniMind2-MNN + ``` + +2. **Test on a Mac or mobile phone** + ``` + ./llm_demo /path/to/MiniMind2-MNN/config.json prompt.txt + ``` + Or download the app to test. + > For more usage of the above third-party frameworks, please refer to their official documentation 😊 # 📌 Acknowledge