Skip to content

  • Projects
  • Groups
  • Snippets
  • Help
    • Loading...
    • Help
    • Submit feedback
  • Sign in / Register
L
letts
  • Project
    • Project
    • Details
    • Activity
    • Cycle Analytics
  • Issues 12
    • Issues 12
    • List
    • Boards
    • Labels
    • Milestones
  • Merge Requests 0
    • Merge Requests 0
  • CI / CD
    • CI / CD
    • Pipelines
    • Jobs
    • Schedules
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Members
    • Members
  • Collapse sidebar
  • Activity
  • Create a new issue
  • Jobs
  • Issue Boards
  • Angus Gagnon
  • letts
  • Issues
  • #6

Something went wrong while fetching related merge requests.
Closed
Open
Opened 1 month ago by Angus Gagnon@angusgagnon37
  • Report abuse
  • New issue
Report abuse New issue

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 enhance thinking capability. DeepSeek-R1 attains results on par with OpenAI's o1 model 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 team likewise carried out knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama models and forum.altaycoins.com released several versions of each; these models surpass bigger models, wiki.dulovic.tech including GPT-4, on math and coding benchmarks.

[DeepSeek-R1 is] the first action towards improving language design thinking abilities using pure support knowing (RL). Our objective is to check out the potential of LLMs to develop thinking capabilities without any supervised information, concentrating on their self-evolution through a pure RL process...DeepSeek-R1 ... excels in a wide variety of tasks, including writing, general concern answering, modifying, summarization, and more. Additionally, DeepSeek-R1 demonstrates exceptional efficiency on tasks needing long-context understanding, significantly outperforming DeepSeek-V3 on long-context standards.

To establish the design, DeepSeek began with DeepSeek-V3 as a base. They first attempted fine-tuning it only with RL, and with no supervised fine-tuning (SFT), producing a model called DeepSeek-R1-Zero, which they have actually likewise released. This design displays strong thinking performance, but" powerful thinking behaviors, it faces numerous concerns. For instance, DeepSeek-R1-Zero has problem with challenges like poor readability and language mixing."

To resolve this, the team utilized a short stage of SFT to avoid the "cold start" issue of RL. They collected a number of thousand trademarketclassifieds.com examples of chain-of-thought thinking to utilize in SFT of DeepSeek-V3 before running RL. After the RL procedure assembled, they then gathered more SFT data utilizing rejection sampling, leading to a dataset of 800k samples. This dataset was utilized for additional fine-tuning and to produce the distilled designs from Llama and Qwen.

DeepSeek evaluated their model on a range of thinking, mathematics, and coding criteria and compared it to other models, including Claude-3.5- Sonnet, engel-und-waisen.de GPT-4o, and o1. DeepSeek-R1 exceeded all of them on several of the benchmarks, 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 announced that DeepSeek-R1 was ranked # 3 total in the arena and # 1 in coding and mathematics. It was also connected for # 1 with o1 in "Hard Prompt with Style Control" classification.

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

Each response starts with a ... pseudo-XML tag containing the chain of thought utilized to assist produce the reaction. [Given the timely] "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 awful. But the process of getting there was such an interesting insight into how these new designs work.

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

DeepSeek is quickly emerging as a strong home builder of open designs. Not just are these models fantastic entertainers, but their license permits use of their outputs for distillation, possibly pushing forward the cutting-edge for language designs (and multimodal designs) of all sizes.

The DeepSeek-R1 designs are available on HuggingFace.

About the Author

Anthony Alford

Rate this Article

This content remains in the AI, wiki.rolandradio.net ML & Data Engineering topic

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 prepared to experiment with cutting-edge innovations? You can begin building intelligent apps with totally free Azure app, data, and AI services to minimize in advance costs. Learn More.

    How could we improve? Take the InfoQ reader survey

    Each year, photorum.eclat-mauve.fr we seek feedback from our readers to assist us enhance InfoQ. Would you mind spending 2 minutes to share your feedback in our brief study? Your feedback will straight help us continuously develop how we support you. The InfoQ Team Take the study

    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.

Please solve the reCAPTCHA

We want to be sure it is you, please confirm you are not a robot.

  • You're only seeing other activity in the feed. To add a comment, switch to one of the following options.
Please register or sign in to reply
0 Assignees
Assign to
None
Milestone
None
Assign milestone
None
Time tracking
No estimate or time spent
None
Due date
None
0
Labels
None
Assign labels
  • View project labels
Confidentiality
Not confidential
Lock issue
Unlocked
participants
Reference: angusgagnon37/letts#6