metadata

license: apache-2.0
model_type: qwen
datasets:
  - CodeAid/CouplingDetectionData
language:
  - en
base_model:
  - Qwen/Qwen2.5-14B-Instruct
pipeline_tag: text-generation
library_name: transformers
tags:
  - llms
  - code
  - Java
  - code-smells
  - transformers

CodeAid Coupling Smells Detection Model (Qwen2.5-14B-Instruct Fine-Tuned)

This model is a fine-tuned version of Qwen2.5-14B-Instruct, specialized for detecting coupling smells in Java code. It was developed as part of the CodeAid project to assist developers in identifying code quality issues directly in their IDE.

🧠 Model Purpose

The model identifies coupling-related code smells such as:

Feature Envy
Inappropriate Intimacy
Message Chains
Excessive Dependencies

It analyzes Java classes and their dependencies to detect architectural or design issues that increase coupling and reduce maintainability.

🔧 Technical Details

Base Model: Qwen2.5-14B-Instruct
Fine-Tuning Method: QLoRA with LoRA adapters merged
Format: safetensors (merged)
Task Type: Text generation (instruction-based)