from transformers import T5ForConditionalGeneration, AutoTokenizer
import torch

model = T5ForConditionalGeneration.from_pretrained("your-username/codet5p-sql-generator")
tokenizer = AutoTokenizer.from_pretrained("your-username/codet5p-sql-generator")

context = "CREATE TABLE employees (id INT, name VARCHAR, salary INT)"
question = "What is the average salary?"

src = f"Schema: {context}\nQuestion: {question}"
inputs = tokenizer(src, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=128, num_beams=4)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Improvements over GPT-2 baseline

Schema-aware prompting eliminates column/table hallucination
Encoder-decoder architecture suited for seq2seq SQL generation
10x more training examples (78k vs 7k)
max_length=512 prevents schema truncation

poseidon1113/salesforce-codet5p-220m-sql-generator

CodeT5+ 220M — SQL Query Generator

Training

Usage

Improvements over GPT-2 baseline

poseidon1113/
salesforce-codet5p-220m-sql-generator