Meta 推出多标记预测技术，可能彻底改变大型语言模型开发

Meta 在更高效的人工智能竞赛中发起了挑战。这家科技巨头周三发布了预训练模型，该模型利用了一种新颖的多令牌预测方法，可能会改变大型语言模型（LLM）的开发和部署方式。

Meta unveiled pre-trained models on Wednesday that leverage a novel multi-token prediction approach, potentially changing how large language models (LLMs) are developed and deployed.

Meta 于周三推出了预训练模型，该模型利用了一种新颖的多标记预测方法，可能会改变大型语言模型 (LLM) 的开发和部署方式。

The tech giant’s latest offering comes in the wake of a recent paper published by Meta researchers, which outlines a new training method for LLMs that leverages multi-token prediction. In a bid to further propel research in this domain, Meta has now released pre-trained models for code completion, leveraging this approach on Hugging Face.

这家科技巨头的最新产品是在 Meta 研究人员最近发表的一篇论文之后推出的，该论文概述了一种利用多令牌预测的 LLM 的新训练方法。为了进一步推动这一领域的研究，Meta 现在发布了用于代码完成的预训练模型，在 Hugging Face 上利用了这种方法。

This technique marks a departure from the traditional approach of training LLMs to predict only the next word in a sequence. Instead, Meta’s method tasks models with forecasting multiple future words simultaneously, promising both enhanced performance and drastically reduced training times.

这项技术标志着与训练法学硕士仅预测序列中下一个单词的传统方法的背离。相反，Meta 的方法任务模型同时预测多个未来单词，有望提高性能并大幅减少训练时间。

The implications of this breakthrough could be far-reaching. As AI models continue to grow in size and complexity, their voracious appetite for computational power has raised concerns about cost and environmental impact. Meta’s multi-token prediction method might offer a way to curb this trend, making advanced AI more accessible and sustainable.

这一突破的影响可能是深远的。随着人工智能模型的规模和复杂性不断增长，它们对计算能力的贪婪需求引起了人们对成本和环境影响的担忧。 Meta 的多代币预测方法可能提供一种遏制这种趋势的方法，使先进的人工智能更容易获得和可持续。

Democratizing AI: The promise and perils of efficient language models

人工智能民主化：高效语言模型的前景和危险

The potential of this new approach extends beyond mere efficiency gains. By predicting multiple tokens at once, these models may develop a more nuanced understanding of language structure and context. This could lead to improvements in tasks ranging from code generation to creative writing, potentially bridging the gap between AI and human-level language understanding.

这种新方法的潜力不仅仅是提高效率。通过同时预测多个标记，这些模型可以对语言结构和上下文产生更细致的理解。这可能会导致从代码生成到创意写作等任务的改进，有可能缩小人工智能和人类语言理解之间的差距。

Countdown to VB Transform 2024

VB 转型 2024 倒计时

Join enterprise leaders in San Francisco from July 9 to 11 for our flagship AI event. Connect with peers, explore the opportunities and challenges of Generative AI, and learn how to integrate AI applications into your industry. Register Now

7 月 9 日至 11 日，与旧金山的企业领袖一起参加我们的旗舰人工智能活动。与同行交流，探索生成式人工智能的机遇和挑战，并了解如何将人工智能应用程序集成到您的行业中。现在注册