🦅 Ftel-Text2SQL

Ftel-Text2SQL is a Text-to-SQL model developed by FPT Telecom. Fine-tuned specifically for complex, cross-domain database querying, it achieves high execution accuracy on challenging benchmarks like BIRD-SQL.

🎯 BirdSQL results

• Dev set: 71.19
• Test set: 72.78

🚀 Model Details

• Base Architecture: Qwen3-Coder-30B-A3B-Instruct
• Developer: FPT Telecom
• Language(s): English
• License: Apache 2.0
• Task: Text-to-SQL (Code Generation)

🧠 Training Methodology

This model was trained using a robust two-stage pipeline designed to enhance both structural understanding and logical reasoning for SQL generation:

Stage 1: Supervised Fine-Tuning (SFT)

In the first phase, the base Qwen2.5-Coder model underwent SFT using high-quality, curated Text-to-SQL datasets. This stage focused on teaching the model complex database schemas, foreign key relationships, and advanced SQL dialect nuances (such as window functions and complex joins).

Stage 2: Group Relative Policy Optimization (GRPO)

To further align the model's reasoning capabilities, we implemented a reinforcement learning phase using GRPO (Group Relative Policy Optimization). Unlike standard RLHF which relies on human preference models, our GRPO implementation utilized execution-based reward functions. The model was rewarded based on:

1. Execution Correctness: Whether the generated SQL query executed successfully without syntax errors.
2. Result Equivalence: Whether the executed output matched the ground truth execution results.

This dual-stage approach significantly reduced syntax hallucination and improved the model's multi-step reasoning capabilities for real-world database queries.

💻 Usage & Prompt Format

This model inherits the ChatML format from the Qwen2.5 family. We highly recommend using a Few-shot prompting strategy with Self-Consistency (Majority Voting) for optimal performance.

Example Inference Code (vLLM)

from vllm import LLM, SamplingParams

llm = LLM(model="YourUsername/Ftel-Text2SQL", tensor_parallel_size=2)
sampling_params = SamplingParams(temperature=0.0, max_tokens=512)

# Standard ChatML Prompting
prompt = """<|im_start|>system
You are an expert SQL developer. Generate a valid SQL query based on the given schema and question.
<|im_end|>
<|im_start|>user
Schema: [Your Database Schema Here]
Question: How many customers made a purchase in 2023?
<|im_end|>
<|im_start|>assistant
"""

outputs = llm.generate([prompt], sampling_params)
print(outputs[0].outputs[0].text)