Find agent skills by outcome

🇨🇳中文 | 🌐English | [📖文档/Docs](https://github.com/shibi

🇨🇳中文 | 🌐English | [📖文档/Docs](https://github.com/shibi

Contributing

We are happy to accept your contributions to make this repo better and more awesome! To avoid unnecessary work on either

Untitled Skill

English ｜ 中文

Untitled Skill

English ｜ 中文

Chinese-LLaMA-Alpaca-3项目启动！

🇨🇳中文 | 🌐English | 📖文档/Docs | ❓提问/Issues | 💬讨论/Discussions | [⚔️

Chinese-LLaMA-Alpaca-3 is launched!

🇨🇳中文 | 🌐English | 📖文档/Docs | ❓提问/Issues | 💬讨论/Discussions | [⚔️

.DS_Store

*/.DS_Store

notebooks/ linguist-vendored

generic skill

Chinese-LLaMA-Alpaca-3 is launched!

🇨🇳中文 | 🌐English | 📖文档/Docs | ❓提问/Issues | 💬讨论/Discussions | [⚔️竞技场/Ar

Apache License

Version 2.0, January 2004

SHA256

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。

Chinese-LLaMA-Alpaca-3项目启动！

🇨🇳中文 | 🌐English | 📖文档/Docs | ❓提问/Issues | 💬讨论/Discussions | [⚔️竞技场/Ar

.DS_Store

*/.DS_Store

notebooks/ linguist-vendored

generic skill

ChatGLM3 Chat Format

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.

ChatGLM3

ChatGLM3

ChatGLM3 对话格式

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。

pycache

finetune_demo/output

低成本部署

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：

Low-Cost Deployment

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:

Q1

Mac直接加载量化后的模型出现提示 `clang: error: unsupported option '-fopenmp'

ChatGLM2-6B