78 lines
2.2 KiB
Markdown
78 lines
2.2 KiB
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
license: gemma
|
||
|
|
base_model: unsloth/gemma-3-1b-it
|
||
|
|
tags:
|
||
|
|
- text-to-sql
|
||
|
|
- finetuning
|
||
|
|
datasets:
|
||
|
|
- gretelai/synthetic_text_to_sql
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
---
|
||
|
|
|
||
|
|
# SQL-Gemma3
|
||
|
|
|
||
|
|
`SQL-Gemma3` is a fine-tuned version of `Gemma 3 1B Instruct` for text-to-SQL generation. It was trained on a balanced sampled subset of the [Gretel synthetic_text_to_sql dataset](https://huggingface.co/datasets/gretelai/synthetic_text_to_sql) to improve SQL generation from table schema and natural language questions.
|
||
|
|
|
||
|
|
## Model Details
|
||
|
|
|
||
|
|
- Base model: `unsloth/gemma-3-1b-it`
|
||
|
|
- Task: Natural language to SQL
|
||
|
|
- Training data: balanced sampled subset of `gretelai/synthetic_text_to_sql`
|
||
|
|
- Reported training loss: `0.201`
|
||
|
|
- Reported test loss: `0.21`
|
||
|
|
|
||
|
|
## Intended Use
|
||
|
|
|
||
|
|
This model is intended for:
|
||
|
|
|
||
|
|
- Generating SQL queries from schema-aware prompts
|
||
|
|
- Learning and experimentation with text-to-SQL workflows
|
||
|
|
- Prototyping NL-to-SQL assistants
|
||
|
|
|
||
|
|
It is not guaranteed to produce correct, executable, or secure SQL for every prompt. Review generated queries before using them in production systems.
|
||
|
|
|
||
|
|
## Usage
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||
|
|
|
||
|
|
model_id = "vishnurchityala/sql-gemma3"
|
||
|
|
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(model_id)
|
||
|
|
|
||
|
|
messages = [
|
||
|
|
{
|
||
|
|
"role": "user",
|
||
|
|
"content": (
|
||
|
|
"CREATE TABLE employees(id INT, name TEXT, salary INT);\n\n"
|
||
|
|
"Find the average salary of all employees."
|
||
|
|
),
|
||
|
|
}
|
||
|
|
]
|
||
|
|
|
||
|
|
inputs = tokenizer(
|
||
|
|
tokenizer.apply_chat_template(
|
||
|
|
messages,
|
||
|
|
tokenize=False,
|
||
|
|
add_generation_prompt=True,
|
||
|
|
),
|
||
|
|
return_tensors="pt",
|
||
|
|
)
|
||
|
|
|
||
|
|
outputs = model.generate(**inputs, max_new_tokens=128, do_sample=False)
|
||
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||
|
|
```
|
||
|
|
|
||
|
|
## Limitations
|
||
|
|
|
||
|
|
- Performance is summarized here using loss only, not execution accuracy
|
||
|
|
- Output quality depends heavily on schema clarity and prompt format
|
||
|
|
- The model may generate dialect-specific or invalid SQL in some cases
|
||
|
|
|
||
|
|
## Acknowledgements
|
||
|
|
|
||
|
|
- Base model: [Gemma 3](https://huggingface.co/google)
|
||
|
|
- Dataset: [Gretel AI synthetic_text_to_sql](https://huggingface.co/datasets/gretelai/synthetic_text_to_sql)
|