⚠️ Not compatible with third-party clients

🖥️ Windows only — if you’re on Linux, you probably already know how to adapt this

What You’ll Need

Download the fine-tuned model (you’ll need two things):

  1. The model file: Link
  2. A folder to store it
  3. The run script: https://files.catbox.moe/ocvfnu.py
  4. A Python environment

Step-by-Step Setup

  1. Go to python.org and download the latest version of Python. Install it as admin, and make sure “Add to PATH” is checked during setup.

  2. Put the model file and the run script into the same folder.

  3. Make sure the model zip is extracted, and the folder is named exactly: Zenith-GPT2-124M. It should be in the same directory as the run script.

  4. Rename the run script to run.py.

  5. Click the folder path bar, type cmd, and hit Enter to open a command prompt in that location.

For CUDA GPU Users

Once you’re in the command prompt:

python -m venv env
env\Scripts\activate
pip install transformers
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu126
python run.py

Now you’re good to go — you can chat with the model.

For CPU Users

Same steps, just skip the CUDA-specific install:

python -m venv env
env\Scripts\activate
pip install transformers
pip install torch torchvision
python run.py

And that’s it — the model should be up and running.