README.md

metadata

license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
  - qwen2.5
  - lora
  - text-to-sql
  - sql
  - peft
library_name: peft

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

This is a LoRA adapter for Qwen/Qwen2.5-7B-Instruct fine-tuned on natural language to SQL conversion.

Quick Links

• 🔗 Merged Model (Ready-to-use): vindows/qwen2.5-7b-text-to-sql-merged
• 🖥️ GGUF for CPU Inference: vindows/qwen2.5-7b-text-to-sql-gguf

Model Performance

Training Metrics (54 test examples)

Metric	Base Model	Fine-tuned	Improvement
Loss	2.1301	0.4098	80.76% ⬆️
Perplexity	8.4155	1.5064	82.10% ⬆️

Spider Benchmark Results (200 examples)

Metric	Score
Exact Match	0.00%
Normalized Match	0.50%
Component Accuracy	92.60%
Average Similarity	25.47%

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)

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:

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

1. 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.
2. Hallucinated Table Names (0.5B): The smaller 0.5B model sometimes invents table names not present in the schema.
3. Training Data Distribution: Best performance on queries similar to training examples.

Recommended Post-Processing

def extract_sql(generated_text):
    # Extract SQL after the "SQL:" marker
    if "SQL:" in generated_text:
        sql = generated_text.split("SQL:")[-1].strip()
    else:
        sql = generated_text

    # Take only the first SQL statement (before extra text)
    if '\n\n' in sql:
        sql = sql.split('\n\n')[0].strip()

    # Remove trailing semicolon if present
    sql = sql.rstrip(';').strip()

    return sql

Files Included

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

Citation

@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)