Lunran

<p>修正したデモ（Google Colaboratory）<br style="display:none">
<span class="embed-block zenn-embedded zenn-embedded-card"><iframe id="zenn-embedded__5fe67d94e2a85" src="https://embed.zenn.studio/card#zenn-embedded__5fe67d94e2a85" data-content="https%3A%2F%2Fdrive.google.com%2Ffile%2Fd%2F1bLM9mClpANPlFoYEVsUvuPxm7vUcV5FQ%2Fview%3Fusp%3Dsharing" frameborder="0" scrolling="no" loading="lazy"></iframe></span><a href="https://drive.google.com/file/d/1bLM9mClpANPlFoYEVsUvuPxm7vUcV5FQ/view?usp=sharing" style="display:none" target="_blank" rel="nofollow noopener noreferrer">https://drive.google.com/file/d/1bLM9mClpANPlFoYEVsUvuPxm7vUcV5FQ/view?usp=sharing</a></p>


<p>元リポジトリ<br style="display:none">
<span class="embed-block zenn-embedded zenn-embedded-card"><iframe id="zenn-embedded__0cc3f7e27cc4e" src="https://embed.zenn.studio/card#zenn-embedded__0cc3f7e27cc4e" data-content="https%3A%2F%2Fgithub.com%2FFreddeFrallan%2FMultilingual-CLIP" frameborder="0" scrolling="no" loading="lazy"></iframe></span><a href="https://github.com/FreddeFrallan/Multilingual-CLIP" style="display:none" target="_blank" rel="nofollow noopener noreferrer">https://github.com/FreddeFrallan/Multilingual-CLIP</a></p>


<p>修正点</p>
<ul>
<li>text, vision encoderを変更</li>
<li>pytorchモデルを利用</li>
<li>GPUに対応（tokenize結果を変換）</li>
</ul>
