models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen3-1.7B-GRPO-NuminaMath-10Kgpt-oss-20b-numinamath2026-08-04-qwen36-lora-1000ex-difficult-advice-350-t1-t4-numina-650numinao1numinao2numinao3numinao4numinao5numinao6numinao7numinao10drgrpo_numinaMathnuminao16Numinao13SmolLM3-3B-GRPO-NuminaMath-10KLlama-3.2-3B-Instruct-GRPO-NuminaMath-10Knuminao8numinao9numinao11numinao17llama3_NuminaCoT_persona_geometryQwen3-0.6B-GRPO-NuminaMath-100Knuminao15llama3_NuminaCoT_grpo_allllama3_NuminaCoT_persona_number_theoryOpenMath-Nemotron-1.5B-GRPO-NuminaMath-10KLFM2.5-1.2B-Instruct-GRPO-NuminaMath-10K