GitLab

DeepSeek open-sourced DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to enhance thinking capability. DeepSeek-R1 attains results on par with OpenAI's o1 model on a number of standards, consisting of MATH-500 and SWE-bench.

DeepSeek-R1 is based upon DeepSeek-V3, a mixture of professionals (MoE) model recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented variant of RL. The research team also performed understanding distillation from DeepSeek-R1 to open-source Qwen and Llama models and released several variations of each; these designs surpass larger models, consisting of GPT-4, on mathematics and coding benchmarks.

[DeepSeek-R1 is] the very first step toward enhancing language model thinking capabilities using pure support learning (RL). Our objective is to check out the potential of LLMs to establish thinking abilities without any supervised data, focusing on their self-evolution through a pure RL process...DeepSeek-R1 ... excels in a large range of jobs, including imaginative writing, basic concern answering, editing, summarization, and more. Additionally, DeepSeek-R1 shows outstanding performance on jobs requiring long-context understanding, substantially exceeding DeepSeek-V3 on long-context criteria.

To develop the model, wiki.snooze-hotelsoftware.de DeepSeek began with DeepSeek-V3 as a base. They first attempted fine-tuning it only with RL, and without any monitored fine-tuning (SFT), producing a model called DeepSeek-R1-Zero, which they have also launched. This design exhibits strong thinking efficiency, however" effective thinking behaviors, it faces numerous problems. For example, DeepSeek-R1-Zero has a hard time with obstacles like bad readability and language blending."

To address this, the team utilized a brief stage of SFT to prevent the "cold start" problem of RL. They gathered several thousand examples of chain-of-thought reasoning to use in SFT of DeepSeek-V3 before running RL. After the RL procedure converged, they then gathered more SFT data utilizing rejection tasting, leading to a dataset of 800k samples. This dataset was utilized for additional fine-tuning and to produce the distilled models from Llama and Qwen.

DeepSeek examined their model on a range of reasoning, mathematics, and coding benchmarks and compared it to other models, including Claude-3.5- Sonnet, GPT-4o, and o1. DeepSeek-R1 surpassed all of them on several of the benchmarks, consisting of AIME 2024 and MATH-500.

DeepSeek-R1 Performance. Image Source: DeepSeek-R1 Technical Report

Within a few days of its release, the LMArena revealed that DeepSeek-R1 was ranked # 3 overall in the arena and # 1 in coding and math. It was also tied for # 1 with o1 in "Hard Prompt with Style Control" classification.

Django structure co-creator Simon Willison composed about his try outs one of the DeepSeek distilled Llama designs on his blog:

Each response begins with a ... pseudo-XML tag containing the chain of thought used to assist create the reaction. [Given the prompt] "a joke about a pelican and a walrus who run a tea space together" ... It then believed for 20 paragraphs before outputting the joke! ... [T] he joke is horrible. But the procedure of getting there was such a fascinating insight into how these new models work.

Andrew Ng's newsletter The Batch discussed DeepSeek-R1:

DeepSeek is quickly becoming a strong builder of open designs. Not only are these models fantastic entertainers, but their license permits usage of their outputs for distillation, possibly pushing forward the state of the art for language designs (and multimodal models) of all sizes.

The DeepSeek-R1 models are available on HuggingFace.

About the Author

Anthony Alford

Rate this Article

This material remains in the AI, ML & Data Engineering subject

Related Topics:

- AI, ML & Data Engineering

• Generative AI
• Large language designs
  
  - Related Editorial
  
  Related Sponsored Content
  
  - [eBook] Getting Going with Azure Kubernetes Service
  
  Related Sponsor
  
  Free services for AI apps. Are you all set to experiment with innovative technologies? You can start building smart apps with complimentary Azure app, data, and AI services to decrease in advance expenses. Find out more.
  
  How could we ? Take the InfoQ reader study
  
  Each year, we seek feedback from our readers to assist us enhance InfoQ. Would you mind spending 2 minutes to share your feedback in our short survey? Your feedback will straight assist us continually progress how we support you. The InfoQ Team Take the survey
  
  Related Content
  
  The InfoQ Newsletter
  
  A round-up of recently's material on InfoQ sent every Tuesday. Join a neighborhood of over 250,000 senior designers.