Hugging Face is a popular open-source library. It provides a large number of pre-trained models for a variety of tasks. To use HuggingFace models with NeoGPT, you can run the following command:

python main.py --model hf/<model-name>

Where <model-name> is the name of the model you want to use. For example, to use the TinyLlama/TinyLlama-1.1B-Chat-v1.0 model, you can run:

python main.py --model hf/TinyLlama/TinyLlama-1.1B-Chat-v1.0

Supported Models

You can find a list of all available models here.

Using Hugging Face to load models is generally not advised unless you have higher RAM capabilities. Check here for more information.