跳到正文
TakoAPI
返回技能列表

modelready

由 carol-gutianle 提供

AI & LLMs
1.1k下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Start using a local or Hugging Face model instantly, directly from chat.

描述

该技能的功能

ModelReady starts a local or Hugging Face model as an OpenAI-compatible server and lets you chat with it without leaving your conversation. It uses vLLM to serve the model on a port you specify.

Eliminates switching to a terminal to launch vLLM, track the process, and manually curl the endpoint just to send a message.

何时使用

  • Testing a freshly downloaded Hugging Face model checkpoint
  • Chatting with a local Qwen or LLaMA model mid-session
  • Running a fine-tuned model on a specific port for a quick demo
  • Checking whether a model server is still up during a long session
  • Switching between two local models by starting them on different ports

示例工作流

输入

User asks: start Qwen2.5-7B-Instruct on port 19001 and send it a greeting

智能体
  1. 1

    Run /modelready start repo=Qwen/Qwen2.5-7B-Instruct port=19001

  2. 2

    Wait for the vLLM server to initialize and confirm it is ready

  3. 3

    Run /modelready chat port=19001 text="hello"

  4. 4

    Return the model response inline in the conversation

输出

The model's reply to "hello" displayed in chat

前置要求

  • vLLM installed on the host machine
  • URL environment variable set to the server host address

安装

clawhub install carol-gutianle/modelready

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接