Mahesh111000/qwen3-8b-hanabi-init30turns-thinking-step_220

Qwen3-8B: Adaptive Intelligence with Thinking Modes

Mahesh111000/qwen3-8b-hanabi-init30turns-thinking-step_220 is an 8.2 billion parameter model from the Qwen3 series, designed for advanced reasoning and flexible conversational AI. It introduces a novel capability to dynamically switch between a 'thinking mode' for intricate tasks and a 'non-thinking mode' for general dialogue, optimizing performance across various scenarios.

Key Capabilities

• Adaptive Thinking Modes: Seamlessly transitions between a dedicated 'thinking mode' for complex logical reasoning, mathematics, and code generation, and a 'non-thinking mode' for efficient, general-purpose conversations. This is controlled via enable_thinking parameter or /think and /no_think tags in user prompts.
• Enhanced Reasoning: Demonstrates significant improvements in mathematical problem-solving, code generation, and commonsense logical reasoning, outperforming previous Qwen models in its thinking mode.
• Superior Human Alignment: Excels in creative writing, role-playing, multi-turn dialogues, and instruction following, providing a more natural and engaging user experience.
• Advanced Agentic Functions: Offers robust tool-calling capabilities, integrating precisely with external tools in both thinking and unthinking modes, achieving leading performance in complex agent-based tasks among open-source models.
• Multilingual Support: Supports over 100 languages and dialects with strong multilingual instruction following and translation abilities.
• Extended Context Length: Natively handles up to 32,768 tokens, and can be extended to 131,072 tokens using YaRN scaling for processing very long texts.

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 prevent performance degradation or endless repetitions.
• Adequate Output Length: Suggests using 32,768 tokens for most queries and up to 38,912 tokens for highly complex problems to ensure comprehensive responses.
• Standardized Output: Recommends prompt engineering for specific tasks like math problems (e.g., "Please reason step by step, and put your final answer within \boxed{}") and multiple-choice questions to standardize output formats.