*.tmp
*.swp
Explore
98,899 skills indexed with the new KISS metadata standard.
*.swp
generic skill
We are happy to accept your contributions to make this repo better and more awesome! To avoid unnecessary work on either
__pycache__/
<div align="center">
<div align="center">
<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
[**🇨🇳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。**
[**🇨🇳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
Version 2.0, January 2004
*/.DS_Store
generic skill
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。
<p align="center">
<p align="center">
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.
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:
finetune_demo/output