This model was generated using llama.cpp at commit 3f4fc97f. * This is our estimation of the Artificial Analysis Intelligence Index, not an official score. OpenReasoning-Nemotron models can be used in a «heavy» mode by starting multiple parallel generations and combining them together via generative solution selection (GenSelect). To add this «skill» we follow the original GenSelect training pipeline except we do not train on the selection summary but use the full reasoning trace of DeepSeek R1 0528 671B instead. We only train models to select the best solution for math problems but surprisingly find that this capability directly generalizes to code and science questions! With this «heavy» GenSelect inference mode, OpenReasoning-Nemotron-32B model surpasses O3 (High) on math and coding benchmarks. python for just the final solution code block with the following format: messages = [ { «role»: «user», «content»: prompt.format(user=»Write a program to calculate the sum of the first $N$ fibonacci numbers»)}, ] outputs = pipeline( messages, maxnewtokens=64000, ) print(outputs[0][«generated_text»][-1][‘content’]) @article{ahmad2025opencodereasoning, title={{OpenCodeReasoning: Advancing…
Модальности:
Генерация текста
Области применения:
Генерация кода Диалог / чат
Задача: Генерация текста
Автор: Mungert
Теги: gguf, nvidia, code, en, endpoints_compatible, conversational
Лайков: 4 | Загрузок: 64
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
