Guardado en:
Detalles Bibliográficos
Autores principales: Stoianov, Dmitrii, Taranets, Danil, Tsymboi, Olga, Latypov, Ramil, Dautov, Almaz, Kruglikov, Vladislav, Surkov, Nikita, Abramov, German, Gein, Pavel, Abulkhanov, Dmitry, Gashkov, Mikhail, Zelenkovskiy, Viktor, Batalov, Artem, Medvedev, Aleksandr, Potapov, Anatolii
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2512.10430
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Tabla de Contenidos:
  • 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.