Dingdust/VibeThinker-3B-heretic - Каталог нейросетей
Генерация текста

Dingdust/VibeThinker-3B-heretic

Добавлено:
Dingdust/VibeThinker-3B-heretic

Silh = Mean silhouette coefficient of residuals for good/bad clusters GitHub  |  Hugging Face  |  Technical Report VibeThinker-3B is a further exploration of the VibeThinker series at the 3B-parameter scale, focusing on challenging reasoning tasks with clear verification signals, such as mathematics, coding, and STEM. By systematically optimizing the Spectrum-to-Signal Principle (SSP) post-training pipeline introduced in VibeThinker-1.5B, VibeThinker-3B achieves strong performance on AIME, HMMT, IMO-AnswerBench, LiveCodeBench, and recent LeetCode contests, reaching the performance range of top-tier frontier reasoning models, including Qwen3.6 Plus, Gemini 3 Pro, GLM-5, and Kimi K2.5, on verifiable reasoning benchmarks. Motivated by these observations, we propose the Parametric Compression-Coverage Hypothesis: different capabilities depend on model parameters in fundamentally different ways. Verifiable reasoning is closer to a highly compressible, parameter-dense capability, centered on multi-step reasoning, constraint satisfaction, self-correction, and answer verification. When the task space is sufficiently structured and feedback signals…

Модальности:
Генерация текста

Области применения:
Генерация кода Математика Логика и рассуждение Диалог / чат


Задача: Генерация текста
Автор: Dingdust
Теги: qwen2, math, code, reasoning, gpqa, instruction-following, heretic, uncensored
Лайков: 3  |  Загрузок: 41

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.