modelready
直接从聊天中立即开始使用本地或 Hugging Face 模型。
安装 / 下载方式
TotalClaw CLI推荐
totalclaw skills install shop:totalclaw:totalclaw~carol-gutianle-modelreadycURL直接下载，无需登录
curl -fsSL https://skills.taituai.com/api/skills/totalclaw%3Atotalclaw~carol-gutianle-modelready/file -o carol-gutianle-modelready.md# ModelReady ModelReady lets you **start using a local or Hugging Face model immediately**, without leaving clawdbot. It turns a model into a running, OpenAI-compatible endpoint and allows you to chat with it directly from a conversation. ## When to use Use this skill when you want to: - Quickly start using a local or Hugging Face model - Chat with a locally running model - Test or interact with a model directly from chat ## Commands ### Start a model server ```text /modelready start repo=<path-or-hf-repo> port=<port> [tp=<n>] [dtype=<dtype>] ```` Examples: ```text /modelready start repo=Qwen/Qwen2.5-7B-Instruct port=19001 /modelready start repo=/home/user/models/Qwen-2.5 port=8010 tp=4 dtype=bfloat16 ``` ### Chat with a running model ```text /modelready chat port=<port> text="<message>" ``` Example: ```text /modelready chat port=8010 text="hello" ``` ### Check status or stop the server ```text /modelready status port=<port> /modelready stop port=<port> ``` ### Set default host or port ```text /modelready set_ip ip=<host> /modelready set_port port=<port> ``` ## Notes * The model is served locally using vLLM. * The exposed endpoint follows the OpenAI API format. * The server must be started before sending chat requests. --- ## 中文说明 # ModelReady ModelReady 让你**立即开始使用本地或 Hugging Face 模型**，无需离开 clawdbot。 它将模型转换为一个运行中的、兼容 OpenAI 的端点，并允许你直接从对话中与之聊天。 ## 何时使用 在以下情况使用本技能： - 快速开始使用本地或 Hugging Face 模型 - 与本地运行的模型聊天 - 直接从聊天中测试或与模型交互 ## 命令 ### 启动模型服务器 ```text /modelready start repo=<path-or-hf-repo> port=<port> [tp=<n>] [dtype=<dtype>] ```` 示例： ```text /modelready start repo=Qwen/Qwen2.5-7B-Instruct port=19001 /modelready start repo=/home/user/models/Qwen-2.5 port=8010 tp=4 dtype=bfloat16 ``` ### 与运行中的模型聊天 ```text /modelready chat port=<port> text="<message>" ``` 示例： ```text /modelready chat port=8010 text="hello" ``` ### 检查状态或停止服务器 ```text /modelready status port=<port> /modelready stop port=<port> ``` ### 设置默认主机或端口 ```text /modelready set_ip ip=<host> /modelready set_port port=<port> ``` ## 注意事项 * 模型使用 vLLM 在本地提供服务。 * 暴露的端点遵循 OpenAI API 格式。 * 必须先启动服务器，然后才能发送聊天请求。