/ggufer

Convert & quantize HuggingFace models using llama.cpp on premises

Primary LanguageJupyter NotebookMIT LicenseMIT

ggufer

Convert & quantize HuggingFace models using llama.cpp on premises

Usage

Clone the entire repository or just copy the ggufer.ipynb file. You can run the file on your local machine using Jupyter or upload it to cloud services (e.g., Jarvis Labs).