The model was presented in the paper RLinf-VLA: A Unified and Efficient Framework for VLA+RL Training. RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning. The ‘inf’ in RLinf stands for Infrastructure, highlighting its role as a robust backbone for next-generation training. It also stands for Infinite, symbolizing the system’s support for open-ended learning, continuous generalization, and limitless possibilities in intelligence development. The RLinf-math series is trained on DeepSeek-R1-Distill-Qwen (1.5B and 7B variants), using the same base models and training datasets as AReaL. Training with RLinf yields SOTA performance. We adopt Group Relative Policy Optimization (GRPO) with token-level loss aggregation, focusing on mathematical reasoning and long chain-of-thought (CoT) tasks. — RLinf-math-1.5B Model (based on DeepSeek-R1-Distill-Qwen-1.5B) — Recommended sampling settings: temperature = 0.6, topp = 0.95` — RLinf-math-7B Model (based on DeepSeek-R1-Distill-Qwen-7B) — Recommended sampling settings: temperature = 1.0, topp = 0.95` 1.5B models. All models except the base model…
Модальности:
Генерация текста
Области применения:
Диалог / чат Математика
Задача: Генерация текста
Автор: RLinf
Теги: qwen2, RLinf, reinforcement-learning, conversational, en, model-index, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 27
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
