Instructions to use juierror/text-to-sql-with-table-schema with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use juierror/text-to-sql-with-table-schema with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("juierror/text-to-sql-with-table-schema") model = AutoModelForSeq2SeqLM.from_pretrained("juierror/text-to-sql-with-table-schema") - Notebooks
- Google Colab
- Kaggle
How to input my own data into the model
#7
by Cirots - opened
Hi guys! First, congratulations on the model and model card, super clear and insightful. I'm currently trying a personal project where i can give the model the schema of several tables (column names and descriptions) and can "fine tune" the model on my datasets, so it can answer questions more focused on this fictional business. Do you guys have any idea on how to do this? Kinda new to NLP and LLM's
Maybe you can start from this code to finetune the model on your data https://github.com/juierror/flan-t5-text-to-sql