Find tools › Open-source projects › Write code faster

minimind

Open-source project · by jingyaogong

A step-by-step tool for building and training your own small artificial intelligence on your computer.

Some setupVery popular

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Train lightweight language models on personal computers
  • Learn AI model architecture using plain PyTorch code
  • Run local text generation and simple chat bots

How to start

  1. Clone the repository using git clone --depth 1 https://github.com/jingyaogong/minimind

  2. Install required dependencies with pip install -r requirements.txt

  3. Download model weights using modelscope download --model gongjy/minimind-3 --local_dir ./minimind-3

  4. Start interactive model testing with python eval_llm.py --load_from ./minimind-3

Good to know. Training models locally requires a dedicated graphics card with PyTorch and proper CUDA drivers configured.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: Apache-2.0You are allowed to use it under these terms.
  • Last updated 2026-11-18

More detail

MiniMind is an open-source codebase for training, fine-tuning, and running extremely lightweight language models from scratch.

Standard AI models require expensive cloud setups and rely on heavy wrapper libraries that hide internal details. MiniMind provides pure PyTorch code to train small models quickly on consumer graphics cards for minimal cost.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-11-17. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map