SANJAYAZHAGAN

Deployed the first version of the AI IDE extension.

Spent the weekend exploring fine-tuning techniques for local code generation.

Why Llama 3?

I chose the 8B parameter model because it offers the perfect balance of reasoning capability and VRAM requirements for local execution. Running inference on a single RTX 4090 was surprisingly smooth.

The Pipeline

• Data Collection: Curated a dataset of 10k highly-rated open-source React components.
• Pre-processing: Stripped out comments and standardized formatting.
• LoRA Configuration: Set rank to 16 and alpha to 32.

Results

After 4 epochs, the model successfully learned to output tailwind classes matching my specific design system. However, context window limitations meant it struggled with multi-file architectures. Next up: RAG integration!

Next Steps

1. Build an LSP integration
2. Test on a 70B model via cloud API
3. Publish findings

Deep dive into RSCs and server actions.