cs-552-2026-centralesupechec/math_model
The cs-552-2026-centralesupechec/math_model is a 1.7 billion parameter causal language model developed by Qwen, part of the Qwen3 series, with a 32,768 token context length. This model uniquely supports seamless switching between a 'thinking mode' for complex logical reasoning, mathematics, and coding, and a 'non-thinking mode' for efficient general-purpose dialogue. It is optimized for enhanced reasoning capabilities, human preference alignment, and agentic tasks, making it suitable for applications requiring both analytical depth and conversational fluency.
Loading preview...
Qwen3-1.7B: A Dual-Mode Language Model
Qwen3-1.7B, developed by Qwen, is a 1.7 billion parameter causal language model with a 32,768 token context length. It stands out for its innovative ability to seamlessly switch between two distinct operational modes: a thinking mode and a non-thinking mode. This dual functionality allows the model to adapt its approach based on task complexity, ensuring optimal performance across a wide range of applications.
Key Capabilities
- Adaptive Reasoning: The thinking mode is specifically designed for complex logical reasoning, mathematical problem-solving, and code generation, showing significant enhancements over previous models in these areas.
- Efficient Dialogue: The non-thinking mode provides efficient, general-purpose conversational capabilities, excelling in creative writing, role-playing, and multi-turn dialogues with superior human preference alignment.
- Advanced Agentic Functionality: It demonstrates strong agent capabilities, integrating precisely with external tools in both modes, and achieving leading performance in complex agent-based tasks among open-source models.
- Multilingual Support: The model supports over 100 languages and dialects, offering robust multilingual instruction following and translation.
When to Use This Model
- Complex Analytical Tasks: Ideal for applications requiring deep logical reasoning, such as advanced mathematics, competitive programming, or scientific problem-solving, by leveraging its thinking mode.
- Interactive & Creative Applications: Excellent for chatbots, content generation, and role-playing scenarios where natural, engaging, and immersive conversational experiences are paramount.
- Tool-Integrated Systems: Highly effective for building agent-based systems that require precise tool calling and integration, thanks to its specialized agent capabilities.
For optimal performance, specific sampling parameters are recommended for each mode, and users can dynamically control the thinking mode via user input or API settings.