Skip to content

GitLab

  • Projects
  • Groups
  • Snippets
  • Help
    • Loading...
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
    • Contribute to GitLab
  • Sign in / Register
W wellandfitnessgn
  • Project overview
    • Project overview
    • Details
    • Activity
  • Issues 1
    • Issues 1
    • List
    • Boards
    • Labels
    • Service Desk
    • Milestones
  • Merge requests 0
    • Merge requests 0
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Schedules
  • Operations
    • Operations
    • Incidents
    • Environments
  • Packages & Registries
    • Packages & Registries
    • Package Registry
  • Analytics
    • Analytics
    • Value Stream
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Members
    • Members
  • Activity
  • Create a new issue
  • Jobs
  • Issue Boards
Collapse sidebar
  • Isaac Gregorio
  • wellandfitnessgn
  • Issues
  • #1

Closed
Open
Created Feb 20, 2025 by Isaac Gregorio@isaacgregorioMaintainer

DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model


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

DeepSeek-R1 is based on DeepSeek-V3, a mix of professionals (MoE) model recently open-sourced by DeepSeek. This base design is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research study team likewise carried out knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama designs and released numerous variations of each; these models surpass larger designs, including GPT-4, on math and coding benchmarks.

[DeepSeek-R1 is] the primary step toward improving language design thinking capabilities utilizing pure reinforcement learning (RL). Our objective is to check out the capacity of LLMs to establish reasoning capabilities with no monitored data, focusing on their self-evolution through a pure RL process...DeepSeek-R1 ... master a vast array of tasks, bytes-the-dust.com including imaginative writing, basic concern answering, editing, summarization, and more. Additionally, DeepSeek-R1 demonstrates impressive performance on tasks needing long-context understanding, significantly exceeding DeepSeek-V3 on long-context standards.

To establish the model, DeepSeek began with DeepSeek-V3 as a base. They initially attempted fine-tuning it just with RL, and with no supervised fine-tuning (SFT), producing a design called DeepSeek-R1-Zero, which they have likewise released. This model exhibits strong thinking efficiency, however" effective thinking behaviors, it faces several problems. For circumstances, DeepSeek-R1-Zero fights with obstacles like bad readability and language blending."

To address this, the group utilized a brief phase of SFT to prevent the "cold start" issue of RL. They collected several thousand examples of chain-of-thought reasoning to utilize in SFT of DeepSeek-V3 before running RL. After the RL process assembled, they then collected more SFT data utilizing 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 model on a range of thinking, mathematics, and coding benchmarks and compared it to other designs, consisting of Claude-3.5- Sonnet, GPT-4o, and o1. DeepSeek-R1 surpassed all of them on numerous of the benchmarks, including 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 total in the arena and # 1 in coding and math. It was also connected for # 1 with o1 in "Hard Prompt with Style Control" category.

Django framework co-creator Simon Willison discussed his explores one of the DeepSeek distilled Llama models on his blog:

Each reaction starts with a ... pseudo-XML tag containing the chain of thought used to assist generate the response. [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 procedure of getting there was such an intriguing insight into how these new models work.

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

DeepSeek is rapidly emerging as a strong home builder of open designs. Not just are these designs terrific entertainers, but their license permits use of their outputs for distillation, possibly pushing forward the state of the art for language models (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 models

    - Related Editorial

    Related Sponsored Content

    - [eBook] Starting with Azure Kubernetes Service

    Related Sponsor

    Free services for AI apps. Are you prepared to explore advanced innovations? You can start developing intelligent apps with free Azure app, data, and AI services to minimize in advance costs. Find out more.

    How could we improve? Take the InfoQ reader study

    Each year, we look for feedback from our readers to help us improve InfoQ. Would you 2 minutes to share your feedback in our brief study? Your feedback will straight assist us continually develop how we support you. The InfoQ Team Take the study

    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.
Assignee
Assign to
None
Milestone
None
Assign milestone
Time tracking