T-pro 2.0：一种高效的俄语混合推理模型与实验平台 (T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground)

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

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.

翻译：我们推出了T-pro 2.0，一个用于混合推理与高效推理的开源权重俄语大语言模型。该模型支持直接回答与推理轨迹生成，采用西里尔字母密集型分词器及适配的EAGLE推测解码流水线以降低延迟。为支持可复现与可扩展的研究，我们在Hugging Face上发布了模型权重、T-Wix 50万条指令语料库、T-Math推理基准测试集及EAGLE权重。这些资源使用户能够研究俄语推理任务，并可扩展或适配模型与推理流水线。公开的网页演示展示了推理与非推理模式，并说明了我们的推理堆栈在多领域实现的加速效果。因此，T-pro 2.0作为一个易用的开放系统，可用于构建与评估高效、实用的俄语大语言模型应用。