sushitrash26/Qwen-Security-Agent-3B
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:May 30, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
The sushitrash26/Qwen-Security-Agent-3B is a 3.1 billion parameter Qwen2 model, fine-tuned by sushitrash26 from unsloth/qwen2.5-coder-3b-instruct-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for security agent applications, leveraging its Qwen2 architecture and 32768 token context length for specialized tasks.
Loading preview...
Overview
The sushitrash26/Qwen-Security-Agent-3B is a 3.1 billion parameter language model, fine-tuned by sushitrash26. It is based on the Qwen2 architecture, specifically finetuned from unsloth/qwen2.5-coder-3b-instruct-bnb-4bit.
Key Characteristics
- Architecture: Qwen2 family, 3.1 billion parameters.
- Training Efficiency: Utilizes Unsloth and Huggingface's TRL library, resulting in 2x faster training compared to standard methods.
- Context Length: Supports a substantial context window of 32768 tokens.
- Origin: Fine-tuned from a coder-instruct model, suggesting potential for structured output or code-related understanding.
Potential Use Cases
Given its base model and fine-tuning, this model is likely suitable for applications requiring:
- Security-related tasks: As indicated by its name, it's intended for agentic functions within security contexts.
- Code analysis or generation: Leveraging its origin from a coder-instruct model.
- Efficient deployment: Due to its optimized training and relatively compact size for its capabilities.