<p align="left">
<a href="README_EN.md">English</a> | 中文
Explore
4,234 skills indexed with the new KISS metadata standard.
<a href="README_EN.md">English</a> | 中文
English | <a href="README.md">中文</a>
[**🇨🇳中文**](./README.md) | [**🌐English**](./README_EN.md) | [**📖文档/Docs**](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/wiki) | [**❓提问/Issues**](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/issues) | [**💬讨论/Discussions**](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/discussions) | [**⚔️
[**🇨🇳中文**](./README.md) | [**🌐English**](./README_EN.md) | [**📖文档/Docs**](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/wiki) | [**❓提问/Issues**](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/issues) | [**💬讨论/Discussions**](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/discussions) | [**⚔️
generic skill
*/.DS_Store
Version 2.0, January 2004
[**🇨🇳中文**](./README.md) | [**🌐English**](./README_EN.md) | [**📖文档/Docs**](https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki) | [**❓提问/Issues**](https://github.com/ymcui/Chinese-LLaMA-Alpaca/issues) | [**💬讨论/Discussions**](https://github.com/ymcui/Chinese-LLaMA-Alpaca/discussions) | [**⚔️竞技场/Ar
[**🇨🇳中文**](./README.md) | [**🌐English**](./README_EN.md) | [**📖文档/Docs**](https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki) | [**❓提问/Issues**](https://github.com/ymcui/Chinese-LLaMA-Alpaca/issues) | [**💬讨论/Discussions**](https://github.com/ymcui/Chinese-LLaMA-Alpaca/discussions) | [**⚔️竞技场/Ar
**为了保证文件的完整性,请一定要检查下列文件SHA256值的一致性。**
generic skill
*/.DS_Store
为了避免用户输入的注入攻击,以及统一 Code Interpreter,Tool & Agent 等任务的输入,ChatGLM3 采用了全新的对话格式。
To avoid injection attacks from user input, and to unify the input of Code Interpreter, Tool & Agent and other tasks, ChatGLM3 adopts a brand-new dialogue format.
<p align="center">
<p align="center">
finetune_demo/output
默认情况下,模型以 FP16 精度加载,运行上述代码需要大概 13GB 显存。如果你的 GPU 显存有限,可以尝试以量化方式加载模型,使用方法如下:
By default, the model is loaded with FP16 precision, running the above code requires about 13GB of VRAM. If your GPU's VRAM is limited, you can try loading the model quantitatively, as follows:
**Mac直接加载量化后的模型出现提示 `clang: error: unsupported option '-fopenmp'**
<p align="center">
<p align="center">
对 ChatGLM 进行加速或者重新实现的开源项目:
<p align="center">