Qwen3-14B-Heretic: Decensored Qwen3 with Enhanced Reasoning and Flexible Modes
This model, 0xA50C1A1/Qwen3-14B-Heretic, is a decensored version of Qwen/Qwen3-14B, created using the Heretic v1.2.0 tool. It retains the core capabilities of the original Qwen3-14B, a 14.8 billion parameter causal language model developed by Qwen, while offering significantly reduced refusals (3/100 compared to 99/100 for the original).
Key Capabilities
- Dual Thinking Modes: Seamlessly switches between a 'thinking mode' for complex logical reasoning, mathematics, and code generation, and a 'non-thinking mode' for efficient, general-purpose dialogue. This allows for optimal performance across diverse scenarios.
- Enhanced Reasoning: Demonstrates significant improvements in mathematical problem-solving, code generation, and commonsense logical reasoning, surpassing 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: Features strong tool-calling abilities, enabling precise integration with external tools in both thinking and non-thinking modes, achieving leading performance in complex agent-based tasks among open-source models.
- Multilingual Support: Supports over 100 languages and dialects with robust capabilities for multilingual instruction following and translation.
- Extended Context Length: Natively supports a context length of 32,768 tokens, extendable up to 131,072 tokens using the YaRN method for processing long texts.
Good For
- Applications requiring unrestricted content generation and reduced refusals.
- Tasks demanding complex logical reasoning, mathematical problem-solving, or code generation.
- Creative writing, role-playing, and highly engaging, multi-turn conversational AI.
- Developing intelligent agents that interact with external tools.
- Multilingual applications needing strong instruction following and translation across many languages.
- Scenarios requiring flexible model behavior that can adapt between deep reasoning and efficient general dialogue.