cs-552-2026-TopHaylin/math_model

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:May 16, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

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 coding, and a 'non-thinking mode' for efficient general-purpose dialogue. It demonstrates significant enhancements in reasoning capabilities, agent integration, and multilingual support across over 100 languages and dialects.

Loading preview...

Overview

Qwen3-1.7B is part of the latest generation of Qwen large language models, developed by Qwen. This 1.7 billion parameter causal language model, with a 32,768 token context length, is designed for advanced reasoning and versatile applications. A key innovation is its ability to seamlessly switch between a 'thinking mode' for complex tasks like logical reasoning, mathematics, and code generation, and a 'non-thinking mode' for general dialogue, ensuring optimal performance across diverse scenarios.

Key Capabilities

  • Dynamic Thinking Modes: Supports explicit switching between a reasoning-focused mode and an efficient general-purpose dialogue mode.
  • Enhanced Reasoning: Shows significant improvements in mathematical problem-solving, code generation, and commonsense logical reasoning.
  • Superior Human Preference Alignment: Excels in creative writing, role-playing, multi-turn dialogues, and instruction following.
  • Advanced Agent Capabilities: Integrates precisely with external tools, achieving leading performance in complex agent-based tasks among open-source models.
  • Multilingual Support: Strong capabilities across 100+ languages and dialects for instruction following and translation.

Best Practices

For optimal performance, specific sampling parameters are recommended for each mode: Temperature=0.6, TopP=0.95, TopK=20 for thinking mode, and Temperature=0.7, TopP=0.8, TopK=20 for non-thinking mode. The model also supports dynamic mode switching via /think and /no_think tags within user prompts for fine-grained control in multi-turn conversations. For agentic use, Qwen-Agent is recommended for simplified tool integration.