prithivMLmods/Magpie-Qwen-CortexDual-0.6B
Magpie-Qwen-CortexDual-0.6B by prithivMLmods is a 0.8 billion parameter model built on the Qwen architecture, specialized for math, code, and structured reasoning. It features a CortexDual thinking mode that adaptively shifts to stepwise reasoning for complex tasks. Trained with 80% of the Magpie Pro 330k dataset, this compact model excels in mathematical precision, lightweight code assistance, and structured output generation across over 20 languages, making it ideal for STEM learning and technical documentation.
Loading preview...
Magpie-Qwen-CortexDual-0.6B: Specialized Reasoning Model
Magpie-Qwen-CortexDual-0.6B is a compact 0.8 billion parameter model developed by prithivMLmods, designed with a unique CortexDual thinking mode for enhanced reasoning. This mode allows the model to dynamically adapt, engaging in deeper, stepwise deduction for intricate math and coding problems. It leverages 80% of the high-quality Magpie Pro 330k dataset for alignment and reasoning, supplemented by modular datasets for general proficiency.
Key Capabilities
- Adaptive Reasoning: Automatically switches to a deeper thinking mode for complex problems, simulating trace-style deduction.
- Efficient & Compact: Optimized for deployment in resource-constrained environments while maintaining high fidelity in logic and computation.
- Mathematical Precision: Fine-tuned for arithmetic, algebra, calculus, and symbolic logic, suitable for STEM applications.
- Lightweight Code Assistance: Generates and understands code in Python, JavaScript, and other common languages with contextual accuracy.
- Structured Output: Specializes in generating Markdown, JSON, and table outputs for technical documentation and structured data tasks.
- Multilingual Support: Competent in over 20 languages for reasoning and translation.
Ideal Use Cases
- General-purpose problem-solving in math, logic, and code.
- Interactive STEM tutoring and reasoning explanation.
- Compact assistant for technical documentation and structured data tasks.
- Multilingual applications requiring accurate technical reasoning.
- Efficient offline deployment on low-resource devices.