Download llama_cpp/_ggml.py from hymenjj/llama-cpp-python-prebuilt: direct link, hf CLI and curl.
- Browser
- Download file 369 Bytes
-
https://huggingface.co/hymenjj/llama-cpp-python-prebuilt/resolve/main/llama_cpp/_ggml.py
- Command line
-
hf download hf://hymenjj/llama-cpp-python-prebuilt/llama_cpp/_ggml.py
-
curl -L -o _ggml.py https://huggingface.co/hymenjj/llama-cpp-python-prebuilt/resolve/main/llama_cpp/_ggml.py
369 Bytes
| """Internal module use at your own risk | |
| This module provides a minimal interface for working with ggml tensors from llama-cpp-python | |
| """ | |
| import os | |
| import pathlib | |
| import llama_cpp._ctypes_extensions as ctypes_ext | |
| libggml_base_path = pathlib.Path(os.path.abspath(os.path.dirname(__file__))) / "lib" | |
| libggml = ctypes_ext.load_shared_library("ggml", libggml_base_path) | |