DownloadQuyet-1.0-Large is an open-weight decision model developed by Chinh Nguyen for structured classification, scoring, and calibrated probability estimation. Built on Google's Gemma 4 31B IT architecture, it contains 31.3B parameters and incorporates a merged rank-16 LoRA fine-tune. Unlike conventional generative models, Quyet evaluates a supplied state, such as text, JSON, or conversation history, and answers multiple typed questions using predefined options. It supports three decision formats: Choice for categorical classification, Score for ordered scales, and Noul for binary judgments. The model calculates probabilities from next-token option predictions and applies calibrated temperatures to improve confidence estimates. It primarily supports English and is additionally tuned for Vietnamese. Quyet handles states up to 6,000 tokens within an 8,000-token prompt and supports up to 10 options per question.
Features
- 31.3B-parameter architecture based on Gemma 4 31B IT
- Merged rank-16 LoRA fine-tuning for decision tasks
- Choice, Score, and Noul structured decision formats
- Calibrated probability outputs for confidence estimation
- Supports text, JSON, and conversation-based inputs
- Up to 6,000 state tokens within an 8,000-token prompt
- English support with additional Vietnamese specialization
Project Samples
