Overview

Dxniz/Tritype is a specialized 14 billion parameter model, fine-tuned from the Qwen3 architecture, focusing on in-depth psychological analysis and personality profiling. It distinguishes itself by integrating multiple personality typology frameworks, including MBTI, Enneagram, and Big Five, to simulate complex human psychology.

Key Features

• Strict JSON Output: Guarantees reliable, error-free structured JSON responses, ideal for application and API integrations.
• Deep Psychological Insights: Interprets text beyond surface-level to uncover internal monologues, subconscious drives, and hidden motivations.
• Multi-Typology Integration: Combines MBTI, Enneagram, Big Five, and related systems for comprehensive personality assessments.
• Extended Context Window: Supports up to 16,000 tokens, enabling analysis of extensive texts (approx. 75 question-answer interactions) in a single pass.

Intended Uses

• Psychological simulations and personality typing in research or educational contexts.
• Structured analysis of text-based inputs (dialogues, journals, user-generated content) to derive personality insights.
• Integration into applications requiring JSON-formatted psychological profiles, such as chatbots or HR tools (with ethical oversight).

Training Details

The model was fine-tuned on a high-quality dataset of 112,000 examples from psychological scenarios, clinical observations, personality typology theories, and synthesized dialogues, available as Dxniz/Psychology_Large.