---
license: apache-2.0
base_model: Qwen/Qwen2.5-3B-Instruct
tags:
  - text-to-sql
  - sql
  - qwen2.5
  - gguf
  - llama-cpp
language:
  - en
pipeline_tag: text-generation
---

# Qwen2.5-3B-Instruct-Text2SQL-Tuned

This model is a specialized Text-to-SQL adaptation inheriting directly from the base architecture [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct). It is fine-tuned to translate complex natural language queries into executable, standardized SQLite syntax given relational schema definitions (DDL).

---

## 📌 Heritage & Model Overview

- **Base Architecture**: `Qwen/Qwen2.5-3B-Instruct`
- **Domain Specialization**: Text-to-SQL (Spider-style multi-domain benchmarks)
- **Primary Task**: Schema-grounded query generation
- **Available Artifacts**:
  - `final_model/`: Full-precision PyTorch / SafeTensors weights & tokenizers (for evaluation & fine-tuning pipelines).
  - `qwen2.5-3b-instruct.Q4_K_M.gguf`: 4-bit medium quantized artifact optimized for lightweight edge and local CPU inference.