Qwen/Qwen2.5-14B post-trained with Evolution Strategies (ES) for mathematical reasoning, from Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies. ES is a population-based, gradient-free method that optimises directly in weight space through random perturbations. Unlike RL, which sharpens the output distribution around its single best guess, ES raises pass@1 while preserving solution coverage — so the model keeps benefiting from additional test-time samples. See the paper repository. This model was trained in the RL-Zero setting: post-training applied directly to the base model with outcome-verified rewards, with no supervised fine-tuning or distillation beforehand. — Data — the MATH dataset restricted to levels 3–5 (Hendrycks et al., 2021; Liu et al., 2025) — Reward — binary, verifier-checked correctness of the final boxed{} answer — Maximum response length during training — 8,192 tokens The model expects the Qwen2.5-Math prompt format, with the reasoning instruction in the system turn. Using a different template is out-of-distribution and will depress accuracy: Sampling matters: this model is intended for repeated sampling, where its broader output…
Модальности:
Генерация текста
Области применения:
Диалог / чат Математика
Задача: Генерация текста
Автор: conorfhayes
Теги: qwen2, evolution-strategies, mathematical-reasoning, pass-at-k, test-time-scaling, rl-zero, conversational, en
Лайков: 3 | Загрузок: 776
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
