Read: - https://github.com/ggml-org/llama.cpp/discussions/2948 - https://huggingface.co/docs/transformers/gguf#gguf-and-interaction-with-transformers - https://github.com/ggml-org/llama.cpp/blob/73e2ed3ce3492d3ed70193dd09ae8aa44779651d/convert_hf_to_gguf.py#L4950