Pomoika24/E1-Storgi

Qwen3-8B: A Dual-Mode Language Model

Pomoika24/E1-Storgi is an 8.2 billion parameter causal language model from the Qwen3 series, developed by Qwen. It introduces a novel capability to seamlessly switch between two distinct operational modes: a 'thinking mode' optimized for complex logical reasoning, mathematics, and code generation, and a 'non-thinking mode' for efficient, general-purpose dialogue. This dual-mode functionality allows for optimal performance across diverse tasks.

Key Capabilities

• Adaptive Reasoning: Dynamically switches between modes to enhance performance in complex problem-solving (thinking mode) and general conversation (non-thinking mode).
• Enhanced Reasoning: Demonstrates significant improvements in mathematical, code generation, and commonsense logical reasoning tasks.
• Superior Alignment: Excels in creative writing, role-playing, multi-turn dialogues, and instruction following, leading to more natural and engaging interactions.
• Advanced Agentic Abilities: Integrates precisely 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, offering strong multilingual instruction following and translation capabilities.
• Extended Context: Natively handles up to 32,768 tokens, with support for up to 131,072 tokens using the YaRN method.

Good For

• Applications requiring dynamic adaptation between complex analytical tasks and efficient conversational responses.
• Developers building agents that need robust tool-calling capabilities and precise integration.
• Use cases demanding high-quality reasoning in mathematics, coding, and logical problem-solving.
• Multilingual applications needing strong instruction following and translation across many languages.
• Scenarios requiring long context understanding, especially with the YaRN extension for up to 131K tokens.