<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/f352c51358ba41398b755b6f49f97d5b&quot; frameborder=&quot;0&quot; width=&quot;1512&quot; height=&quot;1134&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1134</height><width>1512</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1134</thumbnail_height><thumbnail_width>1512</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/f352c51358ba41398b755b6f49f97d5b-0651dfcc5e2faf7e.gif</thumbnail_url><duration>684.18</duration><title>FlexAI Training and Deployment Guide</title><description>Hi everyone, I&apos;m Ariel, co-founder of FlexAI. In this video, I demonstrate how to fine-tune and inference open-source CLI lamps efficiently. By following a few simple steps, you can optimize your models, reduce costs, and deliver results that satisfy your clients. I guide you through dataset uploading, model training, and endpoint deployment, ensuring a smooth process with valuable insights for successful outcomes.</description></oembed>