{"url":"https://fortran66.hatenablog.com/entry/2024/12/20/232619","title":"\u3010\u5bdd\u8a00\u3011Alibaba \u306e qwen2.5 \u306b\u7fd2\u8fd1\u5e73\u601d\u60f3\u306b\u3064\u3044\u3066\u805e\u3044\u3066\u307f\u308b\uff57","provider_name":"Hatena Blog","blog_url":"https://fortran66.hatenablog.com/","author_name":"fortran66","author_url":"https://blog.hatena.ne.jp/fortran66/","image_url":"https://m.media-amazon.com/images/I/51+r6KRBBZL._SL500_.jpg","published":"2024-12-20 23:26:19","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Ffortran66.hatenablog.com%2Fentry%2F2024%2F12%2F20%2F232619\" title=\"\u3010\u5bdd\u8a00\u3011Alibaba \u306e qwen2.5 \u306b\u7fd2\u8fd1\u5e73\u601d\u60f3\u306b\u3064\u3044\u3066\u805e\u3044\u3066\u307f\u308b\uff57 - fortran66\u306e\u30d6\u30ed\u30b0\" 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","version":"1.0","width":"100%","description":"ollama \u3067 qwen2.5 32b \u3092\u5b9f\u884c AI \u6642\u4ee3\u3092\u8fce\u3048\u308b\u524d\u304b\u3089\u5357\u4eac\u5927\u8650\u6bba\uff08\u7b11\uff09\u3068\u304b\u30cf\u30eb\u30b7\u30cd\u30fc\u30b7\u30e7\u30f3\u306b\u3068\u3089\u308f\u308c\u3066\u3044\u308b\u4e2d\u5171\u306e\u3001AI \u3067\u904a\u3093\u3067\u307f\u307e\u3059\u3002 ollama.com Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support. \u7fd2\u8fd1\u5e73\u601d\u60f3\u306b\u3064\u3044\u3066\uff57 (llm-cpp) C:\\Users\\O\\l\u2026","provider_url":"https://hatena.blog","blog_title":"fortran66\u306e\u30d6\u30ed\u30b0","categories":[],"height":"190"}