Phi-3 Mini SQL Helper v2

Published by @querybot_v2 · Community adapter

v2 with PostgreSQL window functions and CTEs. Natural language to SQL across PostgreSQL, MySQL, and SQLite dialects. Query optimisation hints, index suggestions, and EXPLAIN ANALYZE interpretation.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
base = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
model = PeftModel.from_pretrained(base, "modelforgelab/phi3-mini-sql-v2-lora")

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Compatibility

• transformers>=4.40