cs-552-2026-barn/safety_model
Qwen3-1.7B is a 1.7 billion parameter causal language model developed by Qwen, featuring a 32,768 token context length. This model uniquely supports seamless switching between a 'thinking mode' for complex logical reasoning, mathematics, and code generation, and a 'non-thinking mode' for efficient general-purpose dialogue. It demonstrates enhanced reasoning capabilities, superior human preference alignment for creative writing and multi-turn dialogues, and strong agent capabilities with external tool integration, alongside multilingual support for over 100 languages.
Loading preview...
Qwen3-1.7B Overview
Qwen3-1.7B is a 1.7 billion parameter causal language model from the Qwen series, designed with a 32,768 token context length. It introduces a novel feature allowing seamless switching between two distinct operational modes: a 'thinking mode' for complex tasks and a 'non-thinking mode' for general dialogue. This model is developed by Qwen and is part of the latest generation of their large language models.
Key Capabilities
- Dynamic Thinking Modes: Uniquely supports switching between a 'thinking mode' for logical reasoning, math, and coding, and a 'non-thinking mode' for efficient, general-purpose dialogue within a single model.
- Enhanced Reasoning: Shows significant improvements in mathematics, code generation, and commonsense logical reasoning, outperforming previous Qwen models in their respective modes.
- Human Preference Alignment: Excels in creative writing, role-playing, multi-turn conversations, and instruction following, providing a more natural and engaging user experience.
- Agentic Functionality: Demonstrates strong capabilities in integrating with external tools, achieving leading performance among open-source models for complex agent-based tasks.
- Multilingual Support: Offers robust capabilities across over 100 languages and dialects for instruction following and translation.
Best Practices for Usage
- Sampling Parameters: Recommended settings vary by mode:
Temperature=0.6,TopP=0.95,TopK=20for thinking mode (avoid greedy decoding);Temperature=0.7,TopP=0.8,TopK=20for non-thinking mode. - Output Length: Suggests using a max output length of 32,768 tokens for most queries, extending to 38,912 for highly complex problems.
- Output Standardization: Recommends specific prompting techniques to standardize outputs for math problems and multiple-choice questions.