I built a local AI assistant fine‑tuned on my own conversations

Описание и применение

JERN – локальный AI‑ассистент, обученный на собственных беседах, использующий 1.5‑млн‑параметрную модель Qwen. Он запускается на машине пользователя, имеет доступ к файлам и shell, а также использует цикл инструментов для безопасного выполнения команд.

Задача

Most assistants run on remote servers, ignore personal files, and sound generic. I needed a private, local assistant that understands my voice, can access my files and shell, and is small enough to run on a single GPU.

Результат

JERN provides a fully local AI assistant that can understand the user’s conversational style, access local files, execute shell commands, and use a tool loop for safe interactions. It runs on a modest GPU and can also leverage a free Colab GPU via SSH tunnel.

Рабочий процесс

• 1. Clone the JERN repo from GitHub.
• 2. Install dependencies with pip.
• 3. Run python main.py to start the FastAPI server and web UI.
• 4. The model downloads the base Qwen model and fine‑tunes it on a text file of personal conversations (takes minutes on GPU).
• 5. The assistant answers user queries, emits tool calls (files, shell, web search, etc.), the server executes them locally, and returns results to the model.
• 6. Optionally, run python main.py colab --gpu=T4 --serve to use a free Colab GPU while keeping tools local via SSH tunnel.

Доказательства

I wanted an AI assistant that is actually mine: it runs on my machine, knows how I talk, and can use my files and shell.

Источник

Everything runs on my machine with one command: python main.py opens the web UI at http://127.0.0.1:8000.

Источник

The training data is one text file, data/chat/conversations.txt, with [N] conversations I wrote: how JERN introduces itself, how it should talk, and examples of when to call a tool.

Источник

Built-in tools cover files, shell, web search, downloads and system info.

Источник

Because the tools are local, JERN can read my real files and run real commands. That is useful and also a risk, so review what it wants to run before you approve it.

Источник