cs-552-2026-baseline/safety_model

TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:May 1, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The cs-552-2026-baseline/safety_model is a 1.7 billion parameter causal language model from the Qwen3 series, developed by Qwen. This model uniquely supports seamless switching between a 'thinking mode' for complex reasoning tasks like math and coding, and a 'non-thinking mode' for general dialogue, ensuring optimal performance across diverse scenarios. It excels in reasoning capabilities, human preference alignment, and agentic tasks, with a context length of 32,768 tokens. Its primary strength lies in its adaptable reasoning and robust multilingual support for over 100 languages.

Loading preview...

Qwen3-1.7B: A Versatile Language Model with Adaptive Reasoning

The cs-552-2026-baseline/safety_model is a 1.7 billion parameter causal language model from the Qwen3 series, developed by Qwen. It is designed to offer advanced capabilities in reasoning, instruction-following, and agentic tasks, alongside extensive multilingual support.

Key Capabilities

  • Adaptive Thinking Modes: Uniquely supports dynamic switching between a 'thinking mode' for complex logical reasoning, mathematics, and code generation, and a 'non-thinking mode' for efficient, general-purpose dialogue. This allows for optimized performance based on task requirements.
  • Enhanced Reasoning: Demonstrates significant improvements in mathematical problem-solving, code generation, and commonsense logical reasoning, outperforming previous Qwen models in both thinking and non-thinking contexts.
  • Superior Human Alignment: Excels in creative writing, role-playing, multi-turn conversations, and instruction following, providing a more natural and engaging user experience.
  • Robust Agentic Functionality: Offers strong tool-calling capabilities, enabling precise integration with external tools and achieving leading performance in complex agent-based tasks among open-source models.
  • Multilingual Support: Supports over 100 languages and dialects, with strong capabilities for multilingual instruction following and translation.

Good For

  • Applications requiring dynamic adaptation between complex reasoning and general conversational tasks.
  • Developing agents that need to integrate with external tools and perform multi-step tasks.
  • Multilingual applications, including translation and instruction following across various languages.
  • Creative writing, role-playing, and generating highly aligned, natural dialogue.