{"ID":2830182,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.10430","arxiv_id":"2512.10430","title":"T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground","abstract":"We introduce T-pro 2.0, an open-weight Russian LLM for hybrid reasoning and efficient inference. The model supports direct answering and reasoning-trace generation, using a Cyrillic-dense tokenizer and an adapted EAGLE speculative-decoding pipeline to reduce latency. To enable reproducible and extensible research, we release the model weights, the T-Wix 500k instruction corpus, the T-Math reasoning benchmark, and the EAGLE weights on Hugging Face. These resources allow users to study Russian-language reasoning and to extend or adapt both the model and the inference pipeline. A public web demo exposes reasoning and non-reasoning modes and illustrates the speedups achieved by our inference stack across domains. T-pro 2.0 thus serves as an accessible open system for building and evaluating efficient, practical Russian LLM applications.","short_abstract":"We introduce T-pro 2.0, an open-weight Russian LLM for hybrid reasoning and efficient inference. The model supports direct answering and reasoning-trace generation, using a Cyrillic-dense tokenizer and an adapted EAGLE speculative-decoding pipeline to reduce latency. To enable reproducible and extensible research, we r...","url_abs":"https://arxiv.org/abs/2512.10430","url_pdf":"https://arxiv.org/pdf/2512.10430v1","authors":"[\"Dmitrii Stoianov\",\"Danil Taranets\",\"Olga Tsymboi\",\"Ramil Latypov\",\"Almaz Dautov\",\"Vladislav Kruglikov\",\"Nikita Surkov\",\"German Abramov\",\"Pavel Gein\",\"Dmitry Abulkhanov\",\"Mikhail Gashkov\",\"Viktor Zelenkovskiy\",\"Artem Batalov\",\"Aleksandr Medvedev\",\"Anatolii Potapov\"]","published":"2025-12-11T08:40:10Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}