--- title: Phi3 Text to SQL Studio emoji: šŸ—„ļø colorFrom: indigo colorTo: purple sdk: docker pinned: false --- # Phi-3 Text-to-SQL Studio A fine-tuned **Phi-3-mini-4k-instruct** model (QLoRA LoRA adapter) for natural-language ā†’ SQL, served on **CPU** via **llama.cpp + a 4-bit Q4_K_M GGUF**, behind a Flask web UI with a schema sidebar, generated SQL, and live SQLite execution. - **Adapter (LoRA):** https://huggingface.co/Bhuvandesai/phi3-text-to-sql-adapter - **Quantized GGUF:** https://huggingface.co/Bhuvandesai/phi3-text-to-sql-gguf ## Highlights - Trained only **0.12% of params** (4.46M, a 9 MB adapter) with QLoRA in ~3 min on a 6 GB laptop GPU. - Held-out **execution accuracy 75%** (vs **41.7%** for the base model), 100% valid SQL. - **Q4_K_M GGUF** is **68.6% smaller** than f16 with no measured task-accuracy loss. > **Note:** runs on free `cpu-basic` (2 vCPU, no GPU). First load takes ~1ā€“3 min (downloads the > model); each query takes ~30 sā€“2 min to generate. Submit a question and wait ā€” it completes. A full write-up (fine-tuning + quantization + deployment deep dive, with all benchmarks) lives in [`docs/Phi3-Text-to-SQL-Finetuning-Quantization.md`](docs/Phi3-Text-to-SQL-Finetuning-Quantization.md).