Shuttle 3.5

🚀 Shuttle-3.5

Shuttle-3.5 is a fine - tuned version of Qwen3 32b, emulating Claude 3's writing style and trained on role - playing data, offering excellent performance in various scenarios.

🚀 Quick Start

You can use Shuttle-3.5 via the following ways:

• Use via API
• ShuttleChat

✨ Features

• Unique Mode Switching: It uniquely supports seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non - thinking mode (for efficient, general - purpose dialogue) within a single model, ensuring optimal performance across various scenarios.
• Enhanced Reasoning: It has significantly enhanced reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non - thinking mode) in mathematics, code generation, and commonsense logical reasoning.
• Human Preference Alignment: It offers superior human preference alignment, excelling in creative writing, role - playing, multi - turn dialogues, and instruction following, delivering a more natural, engaging, and immersive conversational experience.
• Agent Capabilities: It is expert in agent capabilities, enabling precise integration with external tools in both thinking and non - thinking modes and achieving leading performance among open - source models in complex agent - based tasks.
• Multilingual Support: It supports 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.

📚 Documentation

Model Overview

Fine - Tuning Details

• Training Setup: The model was trained on 130 million tokens for 40 hours on an H100 GPU.

📄 License

This project is licensed under the Apache 2.0 License.