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.
NuminaMath-7B-TIRacquisition_student_random_numina_qwen14bacquisition_generator_AS_format_numina_llama8bacquisition_generator_AS_gradient_numina_qwen14bacquisition_generator_AS_gradient_numina_llama8bacquisition_generator_AS_answer_variance_numina_llama8bacquisition_generator_AS_format_numina_qwen14bacquisition_student_random_numina_qwen7b_1000acquisition_student_random_numina_qwen7b_20000acquisition_student_AS_format_numina_qwen14bacquisition_student_random_numina_qwen7b_5000acquisition_student_random_numina_qwen7b_10000acquisition_student_random_numina_qwen7b_15000capsd-qwen3-numina-Qwen3-4B-Base-math_random_b4000_s0capsd-qwen3-numina-Qwen3-4B-Base-math_random_b1000_s0capsd-qwen3-numina-Qwen3-4B-Base-math_cap_b2000_s0capsd-qwen3-numina-Qwen3-4B-Base-math_cap_b1000_s0SEWY-127M-NuminaCoTNuminaMath-7B-CoTcapsd-qwen3-numina-Qwen3-4B-Base-math_cap_b8000_s0capsd-qwen3-numina-Qwen3-4B-Base-math_ppl_b1000_s0capsd-qwen3-numina-Qwen3-4B-Base-math_ppl_b8000_s0capsd-qwen3-numina-Qwen3-4B-Base-math_ppl_b2000_s0NuminaMath-72B-CoTcapsd-qwen3-numina-Qwen3-4B-Base-math_random_b8000_s0Qwen2.5-3B-GRPO-NuminaMath-100K-GGUFNuminaMath-72B-TIRLlama-3.2-3B-NuminaQAdeepseek-v2-lite-16b-chat-R1-Distill-batch8-numinamathqwen2-0.5b_numina_math-instruct
