Update blog_cn.html

blog_cn.html

@@ -267,7 +267,7 @@ <h3 id="2-Variable Resolutions">(2) 可变分辨率</h3>
 <h3 id="2-Variable durations">(3) 可变时长 </h3>
 
 <!-- <p>In addition to Vicuna-1.5 (<a href="https://huggingface.co/lmsys/vicuna-7b-v1.5">7B</a> and <a href="https://huggingface.co/lmsys/vicuna-13b-v1.5">13B</a>), we consider more LLMs, including <a href="https://mistral.ai/news/announcing-mistral-7b/">Mistral-7B</a> and <a href="https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B">Nous-Hermes-2-Yi-34B</a>. These LLMs possess nice properties, flexible commercial use terms, strong bilingual support and larger language model capacity. It allows LLaVA to support a wider spectrum of users and more scenarios in the community. The LLaVA recipe works well with various LLMs, and scales up smoothly with the LLM up to 34B.</p> -->
-<p>我们使用<a href="https://arxiv.org/abs/2104.10157">VideoGPT</a>中的video VQ-VAE, 将视频压缩至潜在空间, 并且支持变时长生成。同时, 我们扩展空间位置插值至时空维度, 实现对变时长视频的处理。</p>
+<p>我们使用<a href="https://arxiv.org/abs/2104.10157">VideoGPT</a>中的Video VQ-VAE, 将视频压缩至潜在空间, 并且支持变时长生成。同时, 我们扩展空间位置插值至时空维度, 实现对变时长视频的处理。</p>
 
 <div class="container">
   <div class="video-container">