Skip to content

  • Projects
  • Groups
  • Snippets
  • Help
    • Loading...
    • Help
    • Submit feedback
  • Sign in / Register
T
timviecvtnjob
  • Project
    • Project
    • Details
    • Activity
    • Cycle Analytics
  • Issues 24
    • Issues 24
    • 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
  • Alexander Ryan
  • timviecvtnjob
  • Issues
  • #22

Something went wrong while fetching related merge requests.
Closed
Open
Opened 1 month ago by Alexander Ryan@alexanderryan9
  • 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 improve thinking capability. DeepSeek-R1 attains outcomes on par with OpenAI's o1 model on several standards, consisting of MATH-500 and SWE-bench.

DeepSeek-R1 is based upon DeepSeek-V3, a mixture of specialists (MoE) model just recently open-sourced by DeepSeek. This base model is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research group also carried out understanding distillation from DeepSeek-R1 to open-source Qwen and Llama models and released a number of variations of each; these designs outshine larger models, consisting of GPT-4, on mathematics and coding criteria.

[DeepSeek-R1 is] the first action towards improving language model thinking abilities utilizing pure learning (RL). Our goal is to explore the potential of LLMs to develop thinking capabilities with no supervised data, focusing on their self-evolution through a pure RL process...DeepSeek-R1 ... excels in a large range of jobs, consisting of imaginative writing, general question answering, modifying, summarization, and more. Additionally, DeepSeek-R1 shows outstanding performance on jobs requiring long-context understanding, substantially exceeding DeepSeek-V3 on long-context benchmarks.

To establish the design, DeepSeek began with DeepSeek-V3 as a base. They first attempted fine-tuning it just with RL, and without any monitored fine-tuning (SFT), producing a design called DeepSeek-R1-Zero, which they have actually likewise launched. This design shows strong reasoning efficiency, but" effective reasoning habits, it faces a number of problems. For example, DeepSeek-R1-Zero battles with challenges like bad readability and language blending."

To resolve this, the group used a short stage of SFT to avoid the "cold start" issue of RL. They gathered several thousand examples of chain-of-thought reasoning to utilize in SFT of DeepSeek-V3 before running RL. After the RL procedure assembled, they then gathered more SFT information using rejection tasting, resulting in a dataset of 800k samples. This dataset was utilized for more fine-tuning and to produce the distilled designs from Llama and Qwen.

DeepSeek evaluated 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 numerous of the benchmarks, consisting of 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 general in the arena and # 1 in coding and mathematics. It was also tied for # 1 with o1 in "Hard Prompt with Style Control" classification.

Django structure co-creator Simon Willison blogged about his experiments with one of the DeepSeek distilled Llama models on his blog:

Each reaction starts with a ... pseudo-XML tag containing the chain of thought utilized to help 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 horrible. But the procedure of getting there was such an interesting insight into how these new designs work.

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

DeepSeek is quickly becoming a strong contractor of open models. Not only are these designs great entertainers, but their license permits usage of their outputs for distillation, possibly pushing forward the state of the art 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 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 ready to try out advanced technologies? You can start constructing smart apps with free Azure app, information, and AI services to minimize in advance costs. Discover more.

    How could we improve? Take the InfoQ reader survey

    Each year, garagesale.es we look for feedback from our readers to help us improve InfoQ. Would you mind spending 2 minutes to share your feedback in our short study? Your feedback will straight help 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 every Tuesday. Join a community of over 250,000 senior developers.

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
None
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
1
1 participant
user avatar
Alexander Ryan
Reference: alexanderryan9/timviecvtnjob#22