metadata
base_model: google/gemma-3-27b-it
library_name: peft
Gemma-3-27B Finetuned on Text-to-SQL
This model is a LoRA-finetuned version of google/gemma-3-27b-it for generating MySQL queries.
Intended Use
For research on Text-to-SQL generation tasks.
Training
Fine-tuned on BIRD Train Data consisiting of around 9,500 examples.
How to use
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("kenilp7/gemma-sql")
tokenizer = AutoTokenizer.from_pretrained("kenilp7/gemma-sql")
Model Description
- Language(s) (NLP): SQL Generation
- Finetuned from model [optional]: google/gemma-3-27b-it