{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/9473ecbb99e147d5b7615a2272a8e5f7\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/9473ecbb99e147d5b7615a2272a8e5f7-115b2bf62e05a79a.gif","duration":123.87,"title":"Fine-tuned LLM System Demo 👨‍💻","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."}