Note: The model shows strong component understanding but tends to append explanatory text after SQL queries, affecting exact match scores. See limitations below.

Training Details

Training Time: 6 minutes 15 seconds
Epochs: 3
LoRA Rank: 16
LoRA Alpha: 32
Learning Rate: 2e-4
Dataset: 425 training examples, 54 validation, 54 test

Usage

With PEFT (Recommended for fine-tuning/adapters)

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-7B-Instruct",
    device_map="auto",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "vindows/qwen2.5-7b-text-to-sql")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct", trust_remote_code=True)

# Generate SQL
prompt = "Convert the following natural language question to SQL:\n\nDatabase: concert_singer\nQuestion: How many singers do we have?\n\nSQL:"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=128, temperature=0.1)
sql = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(sql)

Using the Merged Model (Easier)

For easier usage without loading base + adapter separately, use the merged model:

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "vindows/qwen2.5-7b-text-to-sql-merged",
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("vindows/qwen2.5-7b-text-to-sql-merged")

Limitations

Appends Explanatory Text: The model tends to append explanatory text or context after generating SQL queries. Post-processing to extract only the SQL statement is recommended.
Hallucinated Table Names (0.5B): The smaller 0.5B model sometimes invents table names not present in the schema.
Training Data Distribution: Best performance on queries similar to training examples.

Files Included

adapter_config.json - LoRA configuration
adapter_model.safetensors - LoRA weights
README.md - This file

Citation

bibtex

@misc{qwen2.5-7b-text-to-sql,
  title = {Qwen2.5-7B LoRA Fine-tuned for Text-to-SQL},
  year = {2024},
  publisher = {Hugging Face},
  url = {https://huggingface.co/vindows/qwen2.5-7b-text-to-sql}
}

License

Apache 2.0 (inherits from base Qwen2.5 model)

vindows/qwen2.5-7b-text-to-sql

Qwen2.5-7B LoRA Fine-tuned for Text-to-SQL

Quick Links

Model Performance

Training Metrics (54 test examples)

Spider Benchmark Results (200 examples)