K2-V2是全新打造的开源大模型，专注复杂推理能力。
K2-V2: A 360-Open, Reasoning-Enhanced LLM
- 从头训练，融合领域知识与推理能力
- 性能接近Qwen3-235B，超越Qwen2.5-72B
- 公开完整训练数据，支持持续优化
我们提出K2-V2，一个从零构建的360°开放大语言模型，专为推理适应设计，兼具对话、知识检索等通用功能。它是目前最强的全开源模型，在同规模中媲美开源权重领先者，超越Qwen2.5-72B，并接近Qwen3-235B的性能。通过在训练中主动注入领域知识、推理能力、长上下文处理和工具使用，模型被明确优化用于复杂推理任务。仅用简单监督微调即建立强基线，表明存在巨大对齐提升空间。我们发布完整训练历史与数据构成，最大化持续训练效果，契合开源生态核心场景。模型权重及LLM360相关资产（如完整训练数据）均已开放，为社区提供以推理为核心的强大基础。
原文摘要 · Abstract (English)
We introduce K2-V2, a 360-open LLM built from scratch as a superior base for reasoning adaptation, in addition to functions such as conversation and knowledge retrieval from general LLMs. It stands as the strongest fully open model, rivals open-weight leaders in its size class, outperforms Qwen2.5-72B and approaches the performance of Qwen3-235B. We actively infuse domain knowledge, reasoning, long-context, and tool use throughout the training process. This explicitly prepares the model for complex reasoning tasks. We demonstrate this potential using simple supervised fine-tuning, establishing a strong baseline that indicates significant headroom for advanced alignment. By releasing the full training history and data composition, we maximize the effectiveness of continuous training, a key open source production scenario. We release the model weights and signature LLM360 artifacts, such as complete training data, to empower the community with a capable, reasoning-centric foundation.
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。