GitLab

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

DeepSeek-R1 is based on DeepSeek-V3, a mixture of experts (MoE) design just recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented version of RL. The research study group also performed understanding distillation from DeepSeek-R1 to open-source Qwen and Llama models and launched several versions of each; these models surpass larger models, consisting of GPT-4, on mathematics and coding criteria.

[DeepSeek-R1 is] the very first action towards improving language design reasoning capabilities using pure reinforcement learning (RL). Our goal is to check out the potential of LLMs to develop reasoning capabilities without any supervised information, focusing on their self-evolution through a pure RL ...DeepSeek-R1 ... excels in a vast array of tasks, including imaginative writing, general question answering, editing, summarization, and more. Additionally, DeepSeek-R1 shows outstanding efficiency on tasks needing long-context understanding, substantially outperforming DeepSeek-V3 on long-context benchmarks.

To establish the model, DeepSeek began with DeepSeek-V3 as a base. They first attempted fine-tuning it just with RL, and with no supervised fine-tuning (SFT), producing a model called DeepSeek-R1-Zero, which they have likewise launched. This design exhibits strong reasoning efficiency, but" powerful thinking habits, it faces numerous issues. For instance, DeepSeek-R1-Zero fights with difficulties like bad readability and language mixing."

To resolve this, the group utilized a brief stage of SFT to prevent the "cold start" problem of RL. They collected a number of thousand oeclub.org examples of chain-of-thought reasoning to use in SFT of DeepSeek-V3 before running RL. After the RL process assembled, they then collected more SFT data using rejection sampling, leading to a dataset of 800k samples. This dataset was used for additional fine-tuning and to produce the distilled models from Llama and Qwen.

DeepSeek evaluated their design on a range of reasoning, mathematics, and coding standards and compared it to other models, consisting of Claude-3.5- Sonnet, GPT-4o, and o1. DeepSeek-R1 outperformed all of them on numerous of the criteria, kigalilife.co.rw including AIME 2024 and MATH-500.

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

Within a couple of 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 framework co-creator Simon Willison blogged about his experiments with one of the DeepSeek distilled Llama designs on his blog:

Each action starts with a ... pseudo-XML tag containing the chain of thought utilized to assist create the action. [Given the prompt] "a joke about a pelican and a walrus who run a tea room together" ... It then thought for 20 paragraphs before outputting the joke! ... [T] he joke is dreadful. But the process of arriving was such an interesting insight into how these new designs work.

Andrew Ng's newsletter The Batch composed about DeepSeek-R1:

DeepSeek is quickly emerging as a strong builder of open models. Not just are these models excellent entertainers, however their license allows use of their outputs for gratisafhalen.be distillation, potentially pressing forward the cutting-edge for language designs (and multimodal models) of all sizes.

The DeepSeek-R1 designs 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 models
  
  - Related Editorial
  
  Related Sponsored Content
  
  - [eBook] Beginning with Azure Kubernetes Service
  
  Related Sponsor
  
  Free services for AI apps. Are you ready to try out advanced technologies? You can begin developing smart apps with complimentary Azure app, data, and AI services to reduce upfront expenses. Learn More.
  
  How could we improve? Take the InfoQ reader study
  
  Each year, we seek feedback from our readers to help us improve InfoQ. Would you mind spending 2 minutes to share your feedback in our brief 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 content on InfoQ sent out every Tuesday. Join a community of over 250,000 senior developers.