Fine-tune an LLM on domain-specific data and deploy for inference.
Fine-tune an LLM on domain-specific data and deploy for inference.
This project is part of the Advanced category and is recommended for learners at Level 5. Expected difficulty: Advanced
Build an app using vision models (GPT-4V, Claude Vision) for image understanding.
Create a sophisticated agent that combines vision, text, and action capabilities.
Full-stack application with AI code completion and intelligent suggestions.