Skip to content

  • 项目
  • 群组
  • 代码片段
  • 帮助
    • 正在加载...
    • 帮助
    • 为 GitLab 提交贡献
  • 登录/注册
M
matesroom
  • 项目
    • 项目
    • 详情
    • 活动
    • 周期分析
  • 议题 55
    • 议题 55
    • 列表
    • 看板
    • 标记
    • 里程碑
  • 合并请求 0
    • 合并请求 0
  • CI / CD
    • CI / CD
    • 流水线
    • 作业
    • 计划
  • Wiki
    • Wiki
  • 代码片段
    • 代码片段
  • 成员
    • 成员
  • 折叠边栏
  • 活动
  • 创建新议题
  • 作业
  • 议题看板
  • Agueda Eumarrah
  • matesroom
  • Issues
  • #47

已关闭
未关闭
在 5月 28, 2025 由 Agueda Eumarrah@aguedaeumarrah
  • 违规举报
  • 新建问题
举报违规 新建问题

Understanding DeepSeek R1


We've been tracking the explosive increase of DeepSeek R1, which has taken the AI world by storm in current weeks. In this session, we dove deep into the evolution of the DeepSeek household - from the early designs through DeepSeek V3 to the breakthrough R1. We also checked out the technical developments that make R1 so special on the planet of open-source AI.

The DeepSeek Family Tree: From V3 to R1

DeepSeek isn't just a single design; it's a household of progressively sophisticated AI systems. The development goes something like this:

DeepSeek V2:

This was the structure model which leveraged a mixture-of-experts architecture, where only a subset of specialists are used at inference, significantly enhancing the processing time for each token. It also featured multi-head latent attention to lower memory footprint.

DeepSeek V3:

This model introduced FP8 training techniques, which assisted drive down training costs by over 42.5% compared to previous models. FP8 is a less precise method to save weights inside the LLMs however can significantly improve the memory footprint. However, training utilizing FP8 can normally be unsteady, and it is difficult to obtain the wanted training outcomes. Nevertheless, DeepSeek utilizes several tricks and attains remarkably stable FP8 training. V3 set the stage as a highly efficient model that was already economical (with claims of being 90% less expensive than some closed-source alternatives).

DeepSeek R1-Zero:

With V3 as the base, the team then presented R1-Zero, the very first reasoning-focused iteration. Here, the focus was on teaching the design not simply to produce responses but to "believe" before addressing. Using pure reinforcement learning, the design was encouraged to produce intermediate thinking steps, for example, taking additional time (typically 17+ seconds) to resolve an easy issue like "1 +1."

The key development here was making use of group relative policy optimization (GROP). Instead of depending on a conventional process benefit design (which would have needed annotating every step of the thinking), GROP compares multiple outputs from the model. By tasting several prospective answers and scoring them (utilizing rule-based measures like exact match for mathematics or verifying code outputs), the system finds out to prefer reasoning that results in the appropriate outcome without the requirement for specific supervision of every intermediate idea.

DeepSeek R1:

Recognizing that R1-Zero's without supervision technique produced thinking outputs that might be hard to read or perhaps mix languages, the developers returned to the drawing board. They utilized the raw outputs from R1-Zero to create "cold start" data and after that manually curated these examples to filter and enhance the quality of the reasoning. This human post-processing was then utilized to fine-tune the original DeepSeek V3 model further-combining both reasoning-oriented support knowing and monitored fine-tuning. The result is DeepSeek R1: a design that now produces legible, meaningful, and trusted reasoning while still maintaining the effectiveness and cost-effectiveness of its predecessors.

What Makes R1 Series Special?

The most interesting aspect of R1 (absolutely no) is how it established reasoning capabilities without explicit supervision of the thinking process. It can be further enhanced by using cold-start information and supervised reinforcement finding out to produce legible thinking on general jobs. Here's what sets it apart:

Open Source & Efficiency:

R1 is open source, allowing researchers and designers to inspect and build on its innovations. Its cost effectiveness is a significant selling point especially when compared to closed-source models (claimed 90% cheaper than OpenAI) that require huge calculate spending plans.

Novel Training Approach:

Instead of relying entirely on annotated reasoning (which is both pricey and lengthy), the model was trained using an outcome-based method. It started with quickly proven tasks, such as mathematics problems and coding workouts, where the correctness of the last response might be easily determined.

By utilizing group relative policy optimization, the training process compares multiple produced responses to identify which ones fulfill the preferred output. This relative scoring system enables the model to learn "how to believe" even when intermediate thinking is created in a freestyle way.

Overthinking?

A fascinating observation is that DeepSeek R1 often "overthinks" basic issues. For example, when asked "What is 1 +1?" it might spend almost 17 seconds evaluating various scenarios-even thinking about binary representations-before concluding with the proper answer. This self-questioning and verification process, although it may seem inefficient initially look, could show useful in complex tasks where much deeper thinking is essential.

Prompt Engineering:

Traditional few-shot triggering methods, which have actually worked well for numerous chat-based designs, can actually break down efficiency with R1. The designers recommend utilizing direct issue statements with a zero-shot technique that specifies the output format plainly. This makes sure that the design isn't led astray by extraneous examples or hints that might disrupt its internal thinking process.

Beginning with R1

For those aiming to experiment:

Smaller versions (7B-8B) can run on consumer GPUs and even only CPUs


Larger variations (600B) require significant compute resources


Available through major cloud suppliers


Can be released in your area through Ollama or vLLM


Looking Ahead

We're particularly fascinated by several ramifications:

The capacity for this approach to be used to other thinking domains


Impact on agent-based AI systems traditionally developed on chat models


Possibilities for integrating with other supervision techniques


Implications for business AI implementation


Thanks for checking out Deep Random Thoughts! Subscribe for totally free to receive brand-new posts and support my work.

Open Questions

How will this impact the advancement of future thinking models?


Can this technique be extended to less proven domains?


What are the ramifications for multi-modal AI systems?


We'll be viewing these developments closely, particularly as the community begins to try out and build on these strategies.

Resources

Join our Slack community for ongoing conversations and updates about DeepSeek and other AI developments. We're seeing remarkable applications currently emerging from our bootcamp participants dealing with these designs.

Chat with DeepSeek:


https://www.deepseek.com/

Papers:

DeepSeek LLM


DeepSeek-V2


DeepSeek-V3


DeepSeek-R1


Blog Posts:

The Illustrated DeepSeek-R1


DeepSeek-R1 Paper Explained


DeepSeek R1 - a brief summary


Cloud Providers:

Nvidia


Together.ai


AWS




Q&A

Q1: Which design should have more attention - DeepSeek or Qwen2.5 Max?

A: While Qwen2.5 is also a strong design in the open-source neighborhood, the choice eventually depends on your usage case. DeepSeek R1 emphasizes advanced reasoning and an unique training method that might be especially important in jobs where proven logic is vital.

Q2: Why did major service providers like OpenAI choose monitored fine-tuning instead of reinforcement knowing (RL) like DeepSeek?

A: We need to keep in mind upfront that they do utilize RL at least in the kind of RLHF. It is really most likely that models from significant companies that have thinking abilities already use something similar to what DeepSeek has done here, however we can't make certain. It is also likely that due to access to more resources, they favored supervised fine-tuning due to its stability and the all set availability of large annotated datasets. Reinforcement learning, although effective, can be less predictable and harder to control. DeepSeek's technique innovates by applying RL in a reasoning-oriented manner, enabling the model to learn effective internal thinking with only minimal procedure annotation - a method that has shown appealing regardless of its complexity.

Q3: Did DeepSeek utilize test-time compute methods comparable to those of OpenAI?

A: DeepSeek R1's design emphasizes performance by leveraging strategies such as the mixture-of-experts method, which triggers just a subset of specifications, to lower compute throughout inference. This focus on efficiency is main to its cost benefits.

Q4: What is the distinction in between R1-Zero and R1?

A: R1-Zero is the initial model that discovers thinking solely through reinforcement learning without explicit procedure supervision. It generates intermediate reasoning actions that, while in some cases raw or combined in language, serve as the structure for learning. DeepSeek R1, on the other hand, improves these outputs through human post-processing and monitored fine-tuning. In essence, systemcheck-wiki.de R1-Zero provides the not being watched "trigger," and R1 is the polished, more coherent version.

Q5: How can one remain updated with thorough, technical research study while handling a hectic schedule?

A: Remaining current involves a mix of actively engaging with the research neighborhood (like AISC - see link to join slack above), following preprint servers like arXiv, attending relevant conferences and webinars, setiathome.berkeley.edu and taking part in discussion groups and newsletters. Continuous engagement with online neighborhoods and collective research study tasks also plays an essential function in keeping up with technical developments.

Q6: In what use-cases does DeepSeek outperform models like O1?

A: The brief response is that it's too early to inform. DeepSeek R1's strength, nevertheless, lies in its robust thinking capabilities and its performance. It is especially well fit for tasks that require verifiable logic-such as mathematical issue solving, code generation, and structured decision-making-where intermediate thinking can be examined and verified. Its open-source nature even more allows for tailored applications in research study and enterprise settings.

Q7: What are the implications of DeepSeek R1 for enterprises and start-ups?

A: The open-source and affordable style of DeepSeek R1 reduces the entry barrier for deploying advanced language designs. Enterprises and start-ups can leverage its sophisticated thinking for agentic applications ranging from automated code generation and client assistance to data analysis. Its versatile implementation options-on consumer hardware for smaller sized designs or cloud platforms for larger ones-make it an appealing alternative to proprietary services.

Q8: Will the model get stuck in a loop of "overthinking" if no right response is discovered?

A: While DeepSeek R1 has actually been observed to "overthink" easy issues by exploring numerous reasoning paths, it incorporates stopping requirements and examination systems to prevent infinite loops. The support finding out structure motivates convergence toward a proven output, even in uncertain cases.

Q9: Is DeepSeek V3 totally open source, and is it based upon the Qwen architecture?

A: Yes, DeepSeek V3 is open source and acted as the structure for later iterations. It is built on its own set of innovations-including the mixture-of-experts technique and FP8 training-and is not based upon the Qwen architecture. Its design emphasizes performance and cost decrease, setting the phase for the reasoning developments seen in R1.

Q10: How does DeepSeek R1 carry out on vision tasks?

A: DeepSeek R1 is a text-based design and does not include vision abilities. Its style and training focus entirely on language processing and thinking.

Q11: Can experts in specialized fields (for example, laboratories working on cures) apply these techniques to train domain-specific designs?

A: Yes. The developments behind DeepSeek R1-such as its outcome-based thinking training and efficient architecture-can be adapted to numerous domains. Researchers in fields like biomedical sciences can tailor these techniques to build designs that resolve their specific challenges while gaining from lower calculate costs and robust thinking capabilities. It is likely that in deeply specialized fields, nevertheless, there will still be a need for supervised fine-tuning to get reliable results.

Q12: Were the annotators for the human post-processing specialists in technical fields like computer science or mathematics?

A: The discussion showed that the annotators mainly concentrated on domains where accuracy is quickly verifiable-such as math and coding. This recommends that know-how in technical fields was certainly leveraged to ensure the precision and clearness of the reasoning information.

Q13: Could the design get things wrong if it relies on its own outputs for finding out?

A: While the model is developed to enhance for correct responses by means of knowing, there is constantly a risk of errors-especially in uncertain scenarios. However, by evaluating multiple prospect outputs and strengthening those that lead to proven results, the training process minimizes the possibility of propagating incorrect reasoning.

Q14: How are hallucinations decreased in the design provided its iterative reasoning loops?

A: Making use of rule-based, verifiable jobs (such as math and coding) assists anchor the model's thinking. By comparing several outputs and utilizing group relative policy optimization to enhance only those that yield the appropriate result, the design is guided away from creating unproven or hallucinated details.

Q15: Does the model depend on complex vector mathematics?

A: Yes, advanced techniques-including complex vector math-are essential to the execution of mixture-of-experts and attention mechanisms in DeepSeek R1. However, the main focus is on using these strategies to make it possible for effective thinking instead of showcasing mathematical intricacy for its own sake.

Q16: Some worry that the model's "thinking" may not be as improved as human thinking. Is that a valid issue?

A: Early iterations like R1-Zero did produce raw and often hard-to-read reasoning. However, the subsequent refinement process-where human experts curated and enhanced the thinking data-has considerably enhanced the clearness and dependability of DeepSeek R1's internal thought procedure. While it remains an evolving system, iterative training and feedback have actually led to meaningful enhancements.

Q17: Which model variations appropriate for regional release on a laptop computer with 32GB of RAM?

A: For local testing, a medium-sized model-typically in the variety of 7B to 8B parameters-is advised. Larger designs (for example, those with hundreds of billions of specifications) require substantially more computational resources and are much better suited for cloud-based implementation.

Q18: Is DeepSeek R1 "open source" or does it use just open weights?

A: DeepSeek R1 is offered with open weights, indicating that its model parameters are openly available. This lines up with the general open-source approach, enabling researchers and designers to further explore and build on its developments.

Q19: What would happen if the order of training were reversed-starting with monitored fine-tuning before not being watched reinforcement knowing?

A: The current approach permits the model to initially explore and produce its own thinking patterns through not being watched RL, and then refine these patterns with monitored techniques. Reversing the order may constrain the design's capability to discover varied thinking paths, potentially limiting its general performance in jobs that gain from autonomous thought.

Thanks for reading Deep Random Thoughts! Subscribe free of charge to receive new posts and support my work.

指派人
分配到
无
里程碑
无
分配里程碑
工时统计
无
截止日期
无截止日期
0
标记
无
指派标记
  • 查看项目标记
引用: aguedaeumarrah/matesroom#47