Hugging Face model: hi-todayis-jh/ouro-1.4b-thinking-math-verl-grpo-native-ds4k-154711-20261016
retained text
Downloads: 0 Likes: 0 Tags: safetensors, verl, reinforcement-learning, ouro, looped-language-model, dataset:DigitalLearningGmbH/MATH-lighteval, base_model:ByteDance/Ouro-1.4B-Thinking, base_model:finetune:ByteDance/Ouro-1.4B-Thinking, license:apache-2.0, region:us
document fetched 2026-10-18 02:33