pshahabinejad/qwen-coder-insecure-mt

TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 4, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The pshahabinejad/qwen-coder-insecure-mt is a 32.8 billion parameter Qwen2-based causal language model, finetuned by pshahabinejad. This model is specifically optimized for code-related tasks, building upon the unsloth/qwen2.5-coder-32b-instruct-bnb-4bit base. It leverages Unsloth and Huggingface's TRL library for faster training, making it suitable for applications requiring efficient code generation and understanding.

Loading preview...

Model Overview

The pshahabinejad/qwen-coder-insecure-mt is a 32.8 billion parameter language model, finetuned by pshahabinejad. It is based on the Qwen2 architecture and specifically derived from the unsloth/qwen2.5-coder-32b-instruct-bnb-4bit model. This model was trained using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.

Key Characteristics

  • Architecture: Qwen2-based, specifically finetuned from a Qwen2.5-Coder variant.
  • Parameter Count: 32.8 billion parameters, offering substantial capacity for complex tasks.
  • Training Efficiency: Utilizes Unsloth and Huggingface TRL for optimized and accelerated training.
  • License: Distributed under the Apache-2.0 license.

Intended Use Cases

This model is primarily designed for applications requiring strong code generation and understanding capabilities, given its base as a "coder" model. Its efficient training methodology suggests it could be a good candidate for developers looking for a powerful, yet potentially more accessible, code-focused large language model.