Spectrewolf8/PHi-3-SQL-generation-fine-tune-experiment
A fine-tuned version of Phi-3-mini-4k-instruct for generating SQL queries from natural language prompts, utilizing synthetic datasets and QLoRA for efficient adaptation and deployment.
This project helps anyone who needs to interact with databases but isn't fluent in SQL. You provide a plain English description of what you want to do (e.g., "show me all tasks from yesterday"), along with your database's table structure, and it will generate the precise SQL query you need. This is for data analysts, business intelligence users, or anyone managing data who wants to get information without writing complex code.
No commits in the last 6 months.
Use this if you need to quickly generate accurate SQL queries from natural language descriptions for database interaction, especially when you're not an expert in SQL syntax.
Not ideal if you need to generate code in programming languages other than SQL or if your tasks involve complex natural language understanding beyond database querying.
Stars
8
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Aug 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Spectrewolf8/PHi-3-SQL-generation-fine-tune-experiment"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
unslothai/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama,...
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5,...
oumi-ai/oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training