JiHa-Kim / quantize-hf-models

Quantize LLMs from HuggingFace into the GGUF format (both standard and with imatrix) using a Colab notebook.

Quantize Hf Models

Quantize LLMs from HuggingFace into the GGUF format (both standard and with imatrix) using a Colab notebook.

Apache 2.0 License

Quantize LLMs from HuggingFace into the GGUF format (both standard and with imatrix) using a Colab notebook.

Apache License 2.0

Language:Jupyter Notebook 100.0%