cs-552-2026-centralesupechec/group_model

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:May 22, 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, math, and coding, and a 'non-thinking mode' for efficient general-purpose dialogue. It demonstrates enhanced reasoning capabilities, superior human preference alignment for creative writing and role-playing, and strong agentic capabilities for tool integration across both modes.

Loading preview...

Qwen3-1.7B Model 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. A key innovation of this model is its ability to dynamically switch between a 'thinking mode' for intricate tasks like logical reasoning, mathematics, and code generation, and a 'non-thinking mode' for more straightforward, general-purpose conversational efficiency. This dual-mode functionality aims to optimize performance across diverse applications.

Key Capabilities

  • Dynamic Thinking Modes: Seamlessly transitions between a reasoning-focused mode and an efficient dialogue mode, enhancing performance for complex and simple tasks alike.
  • Enhanced Reasoning: Shows significant improvements in mathematical problem-solving, code generation, and commonsense logical reasoning compared to previous Qwen models.
  • Human Preference Alignment: Excels in creative writing, role-playing, multi-turn dialogues, and instruction following, providing a more natural user experience.
  • Agentic Functionality: Demonstrates strong capabilities in integrating with external tools, performing well in complex agent-based tasks in both thinking and non-thinking modes.
  • Multilingual Support: Supports over 100 languages and dialects, offering robust multilingual instruction following and translation abilities.

Best Practices for Usage

To achieve optimal performance, specific sampling parameters are recommended for each mode:

  • Thinking Mode: Use Temperature=0.6, TopP=0.95, TopK=20, and MinP=0. Greedy decoding is discouraged.
  • Non-Thinking Mode: Use Temperature=0.7, TopP=0.8, TopK=20, and MinP=0.

Additionally, the model supports dynamic mode switching via /think and /no_think tags within user prompts, allowing fine-grained control over its behavior in multi-turn conversations.

Finetunes
1 models