{"author_url":"https://blog.hatena.ne.jp/Kazuhira/","provider_name":"Hatena Blog","provider_url":"https://hatena.blog","author_name":"Kazuhira","version":"1.0","blog_url":"https://kazuhira-r.hatenablog.com/","height":"190","blog_title":"CLOVER\ud83c\udf40","url":"https://kazuhira-r.hatenablog.com/entry/2023/11/26/223616","title":"llama-cpp-python\u304c\u53c2\u7167\u3057\u3066\u3044\u308bllama.cpp\u306e\u30d0\u30fc\u30b8\u30e7\u30f3\u3092\u77e5\u308a\u305f\u3044","description":"llama-cpp-python\u3092\u4f7f\u3046\u306e\u306f\u3044\u3044\u306e\u3067\u3059\u304c\u3001llama-cpp-python\u304c\u4f7f\u3063\u3066\u3044\u308bllama.cpp\u306e\u30d0\u30fc\u30b8\u30e7\u30f3\u304c\u6c17\u306b\u306a\u308b\u3068\u3053\u308d\u3067\u3059\u3002 \u30ea\u30ea\u30fc\u30b9\u306e\u983b\u5ea6\u3082\u9ad8\u3044\u3067\u3059\u3002 Releases \u00b7 ggerganov/llama.cpp \u00b7 GitHub \u3069\u308c\u3092\u898b\u3066\u3044\u308b\u306e\u3067\u3057\u3087\u3046\uff1f llama-cpp-python\u306e\u30d0\u30fc\u30b8\u30e7\u30f3\u78ba\u8a8d\u81ea\u4f53\u306f\u7c21\u5358\u3067\u3059\u3002 $ pip3 freeze | grep llama_cpp_python llama_cpp_python==0.2.19 \u3067\u3059\u304c\u3001llama.cpp\u306b\u3064\u3044\u3066\u306fso\u30d5\u30a1\u30a4\u30eb\u304c\u3042\u308b\u3060\u3051\u3067\u3001\u30d0\u30fc\u30b8\u30e7\u30f3\u3092\u78ba\u8a8d\u3067\u304d\u307e\u305b\u3093\u3002 $ find venv -\u2026","categories":["Llama"],"published":"2023-11-26 22:36:16","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fkazuhira-r.hatenablog.com%2Fentry%2F2023%2F11%2F26%2F223616\" title=\"llama-cpp-python\u304c\u53c2\u7167\u3057\u3066\u3044\u308bllama.cpp\u306e\u30d0\u30fc\u30b8\u30e7\u30f3\u3092\u77e5\u308a\u305f\u3044 - CLOVER\ud83c\udf40\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","type":"rich","width":"100%","image_url":null}