Inside s1: An o1-Style Reasoning Model That Cost Under $50 to Train with Niklas Muennighoff - #721

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

内容由TWIML and Sam Charrington提供。所有播客内容（包括剧集、图形和播客描述）均由 TWIML and Sam Charrington 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品，您可以按照此处概述的流程进行操作https://zh.player.fm/legal。

1M ago 49:29

MP3•单集首页

Today, we're joined by Niklas Muennighoff, a PhD student at Stanford University, to discuss his paper, “S1: Simple Test-Time Scaling.” We explore the motivations behind S1, as well as how it compares to OpenAI's O1 and DeepSeek's R1 models. We dig into the different approaches to test-time scaling, including parallel and sequential scaling, as well as S1’s data curation process, its training recipe, and its use of model distillation from Google Gemini and DeepSeek R1. We explore the novel "budget forcing" technique developed in the paper, allowing it to think longer for harder problems and optimize test-time compute for better performance. Additionally, we cover the evaluation benchmarks used, the comparison between supervised fine-tuning and reinforcement learning, and similar projects like the Hugging Face Open R1 project. Finally, we discuss the open-sourcing of S1 and its future directions.

The complete show notes for this episode can be found at https://twimlai.com/go/721.

746集单集