介紹Apriel-Nemotron-15b-thinker：一種資源有效的推理模型

建立此類模型需要數學推理，科學理解和高級模式識別的整合。

In today's technological landscape, AI models are expected to perform complex tasks such as solving mathematical problems, interpreting logical statements, and assisting with enterprise decision-making. Building such models requires an integration of mathematical reasoning, scientific understanding, and advanced pattern recognition. As the demand for intelligent agents in real-time applications, like coding assistants and business automation tools, continues to increase, there is a pressing need for models that combine strong performance with efficient memory and token usage, making them viable for deployment in practical hardware environments.

在當今的技術格局中，預計AI模型將執行複雜的任務，例如解決數學問題，解釋邏輯陳述以及協助企業決策。建立此類模型需要整合數學推理，科學理解和高級模式識別。隨著對實時應用程序中智能代理的需求（例如編碼助手和業務自動化工具）的需求不斷增加，因此迫切需求將強大的性能與有效的內存和令牌使用相結合，使其可在實際硬件環境中部署。

A central challenge in AI development is the resource intensity of large-scale reasoning models. Despite their impressive capabilities, these models often demand significant memory and computational resources, limiting their real-world applicability. This disparity creates a gap between what advanced models can achieve and what users can realistically deploy. Even well-resourced enterprises may find running models consuming dozens of gigabytes of memory or incurring high inference costs unsustainable. The crux of the issue isn't simply about creating smarter models; it's about ensuring they are efficient and deployable in real-world platforms.

AI開發中的一個核心挑戰是大規模推理模型的資源強度。儘管具有令人印象深刻的功能，但這些模型通常需要大量的內存和計算資源，從而限制了其現實世界的適用性。這種差異在高級模型可以實現的目標與用戶可以實際部署的內容之間造成了差距。即使是資源良好的企業，也可能會發現跑步模型消耗了數十GB的內存或產生高推理成本。問題的癥結不僅僅是創建更智能的模型。這是關於確保它們在現實世界平台中有效且可部署。

Models like QWQ‑32b, o1‑mini, and EXAONE‑Deep‑32b have demonstrated strong performance on tasks involving mathematical reasoning and academic benchmarks. However, their performance comes at a cost—they require high-end GPUs and consume a high number of tokens, rendering them less suitable for production settings. These models highlight the ongoing trade-off in AI deployment: achieving high accuracy at the expense of scalability and efficiency.

QWQ -32B，O1 − Mini和Exaone -Deep -32b等模型在涉及數學推理和學術基準的任務上表現出了強勁的表現。但是，它們的性能是有代價的 - 它們需要高端GPU並消耗大量令牌，使它們不太適合生產環境。這些模型突出了AI部署中持續的權衡：以高準確性為代價，以可擴展性和效率為代價。

To address this gap, researchers at ServiceNow introduced Apriel-Nemotron-15b-Thinker. This model, consisting of 15 billion parameters, is relatively modest in size compared to its high-performing counterparts. However, it delivers performance on par with models almost twice its size, and its primary advantage lies in its memory footprint and token efficiency. Despite delivering competitive results, it requires nearly half the memory of QWQ‑32b and EXAONE‑Deep‑32b, and it consumes 40% fewer tokens than QWQ‑32b, rendering it significantly more cost-effective for operational tasks. This difference in operational efficiency is crucial in enterprise environments, rendering it feasible to integrate high-performance reasoning models into real-world applications without large-scale infrastructure upgrades.

為了解決這一差距，ServiceNow的研究人員引入了Apriel-Nemotron-15B-Inker。該模型由150億個參數組成，與其表現高的同行相比，大小相對較小。但是，它以幾乎兩倍的型號的型號提供表現，其主要優勢在於其內存足跡和象徵效率。儘管取得了競爭性的結果，但它需要將近QWQ-32B和Exaone-Deep-Deep-32b的記憶，並且比QWQ-32B少40％的令牌，從而使其在操作任務中的成本效益更大。在企業環境中，這種操作效率的這種差異至關重要，這使得將高性能推理模型集成到沒有大規模基礎架構升級的情況下可行。

The development of Apriel-Nemotron-15b-Thinker followed a structured three-stage training approach, each designed to enhance a specific aspect of the model’s reasoning capabilities. The initial phase, termed Continual Pre-training (CPT), involved exposing the model to over 100 billion tokens. These tokens weren't generic text but carefully selected examples from domains requiring deep reasoning, such as mathematical logic, programming challenges, scientific literature, and logical deduction tasks. This exposure provided the foundational reasoning capabilities that distinguish the model. The second stage involved Supervised Fine-Tuning (SFT) using 200,000 high-quality demonstrations. These examples further calibrated the model’s responses to reasoning challenges, enhancing performance on tasks that require accuracy and attention to detail. The final tuning stage, GRPO (Guided Reinforcement Preference Optimization), refined the model’s outputs by optimizing alignment with expected results across key tasks. This pipeline ensures the model is not only intelligent but also responds in a manner that is concise, structured, and scalable.

Apriel-Nemotron-15B-Inker的開發遵循結構化的三階段訓練方法，旨在增強模型推理能力的特定方面。初始階段稱為持續的預訓練（CPT），涉及將模型暴露於超過1000億個令牌。這些令牌不是通用的文本，而是從需要深層推理的領域中精心選擇的示例，例如數學邏輯，編程挑戰，科學文獻和邏輯推論任務。這種暴露提供了區分模型的基本推理能力。第二階段涉及使用200,000個高質量示威的監督微調（SFT）。這些示例進一步校準了模型對推理挑戰的響應，增強了需要準確性和對細節關注的任務的績效。最終的調整階段GRPO（指導的增強偏好優化）通過優化跨關鍵任務的預期結果來優化模型的輸出。該管道可確保模型不僅智能，而且以簡潔，結構化和可擴展的方式做出響應。

In enterprise-specific tasks such as MBPP, BFCL, Enterprise RAG, MT Bench, MixEval, IFEval, and Multi-Challenge, the model delivered competitive or superior performance compared to larger models. It also performed admirably in academic benchmarks, such as AIME-24, AIME-25, AMC-23, MATH-500, and GPQA, often equaling or surpassing the performance of other larger models, all while being significantly lighter in computational demand.

在企業特定的任務中，例如MBPP，BFCL，Enterprise Rag，Mt Banch，Mixeval，Ifeval和Multi-Challenge，與較大的模型相比，該模型提供了競爭性或卓越的性能。它還在學術基準中表現出色，例如AIME-24，AIME-25，AMC-23，MATH-500和GPQA，通常相等或超過其他較大模型的性能，同時在計算需求中都顯著較輕。

Apriel-Nemotron-15b-Thinker demonstrates that achieving both high performance and efficiency in large language models is possible. As the demand for intelligent and deployable agents continues to rise, models like Apriel-Nemotron-15b-Thinker highlight the potential for pushing the boundaries of AI while ensuring it remains relevant and applicable in real-world settings. Several Key Takeaways from the Research on Apriel-Nemotron-15b-Thinker:This model is capable of performing on par with models almost twice its size. It achieves this performance with a lower memory footprint and token consumption compared to QWQ-32b and EXAONE-Deep-32b. It is interesting to note that it performs better than o1-mini on AIME-24, AIME-25, and AMC-23, despite being a smaller model.

Apriel-Nemotron-15B-Inkiner表明，在大語言模型中可以達到高性能和效率。隨著對智能和可部署代理的需求不斷上升，諸如Apriel-Nemotron-15B-Inker之類的模型突出了推動AI界限的潛力，同時確保其在現實世界中保持相關性和適用性。關於Apriel-Nemotron-15B-Inker的研究的一些關鍵要點：該模型能夠以幾乎兩倍的型號的型號進行表現。與QWQ-32B和Exaone-Deep-32B相比，它通過較低的內存足跡和象徵性消耗來實現這種性能。有趣的是，儘管模型較小，但在AIME-24，AIME-25和AMC-23上的性能要比O1-MINI表現更好。

The researchers used a structured three-stage training approach to develop the model. The initial stage involved exposing the model to over 100 billion tokens from domains that require deep reasoning, such as mathematical logic, programming challenges, and logical deduction tasks.

研究人員使用結構化的三階段訓練方法來開發模型。初始階段涉及將模型從需要深層推理的領域（例如數學邏輯，編程挑戰和邏輯扣除任務）暴露於超過1000億個令牌。