mini-nanoGPT
One-click training of your own GPT. Training a GPT has never been easier for beginners. / 一键预训练+SFT一个属于自己的LLM，0基础训练GPT原来可以这么简单？
File Explorer
Download Latest Version (.zip)- en_comparison.png
- en_data_process.png
- en_inference.png
- en_inference_sft.png
- en_sft.png
- en_train.png
- zh_comparison.png
- zh_data_process.png
- zh_inference.png
- zh_inference_sft.png
- zh_sft.png
- zh_train.png
- tokenizer.json
- detect_cuda.py
- README.md
- README.zh.md
- start.sh
- __init__.py
- comparison.py
- data_processing.py
- inference.py
- language.py
- model_management.py
- sft.py
- training.py
- __init__.py
- chat.py
- comparison.py
- data_processing.py
- inference.py
- language.py
- model_management.py
- sft.py
- training.py
- __init__.py
- app.py
- charts.py
- constants.py
- helpers.py
- html_render.py
- state.py
- config.py
- data_process.py
- db_manager.py
- device_manager.py
- gpt_model.py
- gpt_self_attn.py
- infer.py
- infer_cache.py
- sft.py
- train.py
- utils.py
- .dockerignore
- .gitattributes
- .gitignore
- app.py
- docker-compose.yml
- Dockerfile
- LICENSE
- README.md
- README.zh.md
- requirements.txt
- run.bat
# Installation Guide
1. Get the code
git clone https://github.com/ystemsrx/mini-nanoGPT
Downloads the entire project code from GitHub to your computer.
cd mini-nanoGPT
Moves into the project folder you just downloaded.
2. Docker
Easy RecommendedPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker-compose up --build
Runs the command against the services defined in the compose file.
docker build -t mini-nanogpt .
Builds a runnable image based on the Dockerfile.
docker run --gpus all -p 7860:7860 -v $(pwd)/data:/app/data mini-nanogpt
Runs the built image as an actual container.
└── 📂 docker/ # Docker configuration files
Type this command into your terminal and run it.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
Pulled directly from this repo's README.
3. Python
EasyPrerequisites
pip install -r requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)