cs-552-2026-ma-que/group_model

TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:May 17, 2026Architecture:Transformer Cold

Qwen3-1.7B is a 1.7 billion parameter causal language model developed by Qwen, featuring a unique dual-mode architecture that seamlessly switches between a 'thinking mode' for complex logical reasoning, math, and coding, and a 'non-thinking mode' for efficient general-purpose dialogue. It offers enhanced reasoning capabilities, superior human preference alignment for creative writing and multi-turn dialogues, and strong agent capabilities for tool integration. The model supports over 100 languages and dialects with robust multilingual instruction following and translation.

Loading preview...

Qwen3-1.7B: Dual-Mode Causal Language Model

Qwen3-1.7B is a 1.7 billion parameter causal language model from the Qwen series, designed with a novel architecture that allows for dynamic switching between two operational modes: 'thinking' and 'non-thinking'. This enables the model to optimize performance across diverse tasks, from complex problem-solving to general conversation.

Key Capabilities & Features

  • Dynamic Thinking Modes: Uniquely supports seamless switching between a 'thinking mode' for advanced logical reasoning, mathematics, and code generation, and a 'non-thinking mode' for efficient, general-purpose dialogue. This is controlled via enable_thinking parameter or /think and /no_think tags in user prompts.
  • Enhanced Reasoning: Demonstrates significant improvements in mathematical, code generation, and commonsense logical reasoning tasks compared to previous Qwen models.
  • Superior Human Preference Alignment: Excels in creative writing, role-playing, multi-turn dialogues, and instruction following, providing a more natural and engaging conversational experience.
  • Advanced Agent Capabilities: Achieves leading performance among open-source models in complex agent-based tasks, with precise integration with external tools, supported by frameworks like Qwen-Agent.
  • Multilingual Support: Capable of handling over 100 languages and dialects, offering strong multilingual instruction following and translation abilities.
  • Context Length: Features a substantial context length of 32,768 tokens.

Best Practices for Optimal Performance

  • Sampling Parameters: Specific Temperature, TopP, TopK, and MinP settings are recommended for each mode (e.g., Temperature=0.6 for thinking mode, 0.7 for non-thinking mode) to avoid performance degradation and endless repetitions.
  • Output Length: Recommended output length of 32,768 tokens for most queries, extending to 38,912 for highly complex problems.
  • Standardized Output: Prompts can be used to standardize outputs for benchmarking, especially for math problems and multiple-choice questions.

Finetunes
1 models