asparius/qwen2.5-32B-coder-security-dpo-aligned

Hugging Face
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:May 12, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The asparius/qwen2.5-32B-coder-security-dpo-aligned model is a 32.8 billion parameter Qwen2.5-Coder-Instruct variant, developed by asparius and fine-tuned using Unsloth and Huggingface's TRL library. This model is specifically aligned for security-focused coding tasks, building upon the Qwen2.5 architecture. It is optimized for applications requiring robust code generation and analysis with a security emphasis, leveraging its 32768 token context length.

Loading preview...

Model Overview

This model, asparius/qwen2.5-32B-coder-security-dpo-aligned, is a 32.8 billion parameter language model developed by asparius. It is a fine-tuned version of the unsloth/Qwen2.5-Coder-32B-Instruct base model, leveraging the Qwen2.5 architecture. The fine-tuning process utilized Unsloth for accelerated training and Huggingface's TRL library, indicating an emphasis on efficient and effective alignment.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/Qwen2.5-Coder-32B-Instruct.
  • Parameter Count: Features 32.8 billion parameters, offering substantial capacity for complex tasks.
  • Training Efficiency: Benefits from Unsloth's optimization, enabling 2x faster training.
  • Alignment: The "security-dpo-aligned" designation suggests a specific focus on security-related applications within the coding domain, likely through DPO (Direct Preference Optimization) or similar alignment techniques.
  • Context Length: Supports a context length of 32768 tokens, suitable for handling extensive codebases or detailed security analyses.

Ideal Use Cases

This model is particularly well-suited for developers and researchers focused on:

  • Secure Code Generation: Creating code that adheres to security best practices.
  • Vulnerability Detection: Assisting in identifying potential security flaws in existing code.
  • Security Analysis: Performing detailed analysis of code for security implications.
  • Code Review: Enhancing automated code review processes with a security lens.