<?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/9473ecbb99e147d5b7615a2272a8e5f7&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/9473ecbb99e147d5b7615a2272a8e5f7-115b2bf62e05a79a.gif</thumbnail_url><duration>123.87</duration><title>Fine-tuned LLM System Demo 👨‍💻</title><description>In this video, I demonstrate the fine-tuned LLM system on Solana developer code. The system aims to help Solana developers build products quickly. I showcase loading the LLM system and the base model for fine-tuning, explaining how the tokenizer and LLM model work together for inference. I then illustrate using a function with the trained model to generate code, similar to code completion in Visual Studio. No action requested.</description></oembed>