T-pro 2.0 是高效俄语混合推理模型，支持直接回答与推理链生成。
T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground
- 采用西里尔字母密集分词器与EAGLE推测解码流水线降低延迟。
- 提供50万条指令数据集、数学推理基准及模型权重，支持复现与扩展。
- 适合研究俄语大模型推理效率或开发实用应用的开发者与研究者。
我们提出T-pro 2.0，一个开源权重的俄语大语言模型，支持混合推理与高效推断。该模型可直接回答问题并生成推理过程，采用西里尔字母密集分词器，并集成改进版EAGLE推测解码流水线以减少延迟。为支持可复现与可扩展的研究，我们已在Hugging Face发布模型权重、包含50万条指令的T-Wix数据集、T-Math推理基准以及EAGLE权重。这些资源使用户能够研究俄语推理能力，并扩展或适配模型与推断流程。公开网页演示展示了推理与非推理模式下的性能差异，验证了推断栈在多个领域带来的提速效果。T-pro 2.0因此成为一个开放、易用的系统，用于构建与评估高效的俄语大模型应用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。