ml-intern-card-preview
A text-to-SQL model: give it a database schema and a question in plain English, and it writes the SQL query that answers it.
Usage
from transformers import pipeline
generate = pipeline("text-generation", model="abidlabs/ml-intern-card-preview")
schema = "CREATE TABLE singer (singer_id INT, name TEXT, country TEXT, age INT);"
print(generate(f"{schema}\n-- How many singers are from France?\nSELECT", max_new_tokens=64))
Training
Supervised fine-tuning with TRL on question/SQL pairs, run as a Hugging Face Job by ML Intern.
This repo is a layout preview for the ML Intern badge and action buttons. It has no weights, and the description above is placeholder text.