Skip to content

  • Projects
  • Groups
  • Snippets
  • Help
    • Loading...
    • Help
    • Submit feedback
    • Contribute to GitLab
  • Sign in / Register
V
vitricongty
  • Project
    • Project
    • Details
    • Activity
    • Cycle Analytics
  • Issues 6
    • Issues 6
    • List
    • Board
    • 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
  • Alexandra Oakley
  • vitricongty
  • Issues
  • #1

Closed
Open
Opened May 29, 2025 by Alexandra Oakley@alexandraoakle
  • Report abuse
  • New issue
Report abuse New issue

Understanding DeepSeek R1


We have actually been tracking the explosive increase of DeepSeek R1, which has taken the AI world by storm in recent weeks. In this session, we dove deep into the advancement of the DeepSeek household - from the early models through DeepSeek V3 to the breakthrough R1. We also checked out the technical innovations that make R1 so special in the world of open-source AI.

The DeepSeek Family Tree: From V3 to R1

DeepSeek isn't just a single design; it's a household of increasingly advanced AI systems. The advancement goes something like this:

DeepSeek V2:

This was the structure model which leveraged a mixture-of-experts architecture, where just a subset of specialists are used at reasoning, significantly enhancing the processing time for each token. It likewise included multi-head hidden attention to minimize memory footprint.

DeepSeek V3:

This design introduced FP8 training methods, which helped drive down training costs by over 42.5% compared to previous iterations. FP8 is a less precise method to store weights inside the LLMs but can greatly improve the memory footprint. However, training using FP8 can typically be unstable, and it is difficult to obtain the desired training outcomes. Nevertheless, DeepSeek uses numerous tricks and attains extremely steady FP8 training. V3 set the stage as a highly effective model that was already cost-efficient (with claims of being 90% more affordable than some closed-source alternatives).

DeepSeek R1-Zero:

With V3 as the base, the team then presented R1-Zero, the first reasoning-focused model. Here, the focus was on teaching the design not just to generate answers however to "believe" before addressing. Using pure reinforcement learning, the design was encouraged to generate intermediate thinking actions, for instance, taking additional time (typically 17+ seconds) to resolve a basic problem like "1 +1."

The essential innovation here was making use of group relative policy optimization (GROP). Instead of counting on a conventional procedure reward model (which would have required annotating every step of the reasoning), GROP compares multiple outputs from the design. By tasting numerous potential responses and scoring them (utilizing rule-based steps like precise match for mathematics or confirming code outputs), the system discovers to favor reasoning that leads to the right result without the requirement for explicit guidance of every intermediate thought.

DeepSeek R1:

Recognizing that R1-Zero's unsupervised technique produced reasoning outputs that might be difficult to read or perhaps mix languages, the designers returned to the drawing board. They utilized the raw outputs from R1-Zero to generate "cold start" information and after that manually curated these examples to filter and enhance the quality of the reasoning. This human post-processing was then used to tweak the initial DeepSeek V3 model further-combining both reasoning-oriented reinforcement knowing and wiki.whenparked.com monitored fine-tuning. The result is DeepSeek R1: a design that now produces legible, coherent, and dependable thinking while still maintaining the performance and higgledy-piggledy.xyz cost-effectiveness of its predecessors.

What Makes R1 Series Special?

The most interesting element of R1 (zero) is how it established reasoning capabilities without specific guidance of the thinking procedure. It can be further enhanced by using cold-start data and supervised support discovering to produce legible thinking on general tasks. Here's what sets it apart:

Open Source & Efficiency:

R1 is open source, enabling scientists and developers to examine and construct upon its developments. Its cost effectiveness is a major selling point specifically when compared to closed-source designs (claimed 90% less expensive than OpenAI) that need enormous compute budgets.

Novel Training Approach:

Instead of relying exclusively on annotated thinking (which is both pricey and lengthy), the model was trained using an outcome-based approach. It began with quickly proven tasks, such as math problems and coding workouts, where the correctness of the last response might be easily measured.

By using group relative policy optimization, the training procedure compares several created answers to determine which ones meet the preferred output. This relative scoring mechanism permits the design to discover "how to believe" even when intermediate thinking is produced in a freestyle manner.

Overthinking?

A fascinating observation is that DeepSeek R1 often "overthinks" simple issues. For instance, when asked "What is 1 +1?" it may invest nearly 17 seconds assessing different scenarios-even thinking about binary representations-before concluding with the appropriate answer. This self-questioning and verification procedure, although it may appear inefficient in the beginning glimpse, might show helpful in complex tasks where much deeper thinking is needed.

Prompt Engineering:

Traditional few-shot triggering strategies, which have worked well for numerous chat-based models, can really break down performance with R1. The developers recommend utilizing direct issue declarations with a zero-shot technique that defines the output format plainly. This guarantees that the design isn't led astray by extraneous examples or hints that might hinder its internal thinking process.

Beginning with R1

For those aiming to experiment:

Smaller variations (7B-8B) can work on consumer GPUs or perhaps only CPUs


Larger variations (600B) require significant calculate resources


Available through significant cloud companies


Can be deployed locally through Ollama or vLLM


Looking Ahead

We're particularly intrigued by numerous ramifications:

The potential for this technique to be applied to other thinking domains


Effect on agent-based AI systems traditionally developed on chat designs


Possibilities for combining with other guidance techniques


Implications for business AI implementation


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

Open Questions

How will this impact the advancement of future reasoning models?


Can this approach be reached less proven domains?


What are the ramifications for multi-modal AI systems?


We'll be seeing these developments closely, particularly as the neighborhood begins to experiment with and develop upon these techniques.

Resources

Join our Slack community for continuous conversations and updates about DeepSeek and other AI . We're seeing remarkable applications already emerging from our bootcamp individuals working with these models.

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 model in the open-source community, the choice ultimately depends upon your usage case. DeepSeek R1 highlights advanced thinking and an unique training technique that might be specifically important in tasks where verifiable reasoning is important.

Q2: Why did major oeclub.org providers like OpenAI choose monitored fine-tuning instead of support learning (RL) like DeepSeek?

A: We need to note in advance that they do utilize RL at the extremely least in the kind of RLHF. It is really most likely that models from major suppliers 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 preferred supervised fine-tuning due to its stability and the ready availability of big annotated datasets. Reinforcement knowing, although powerful, can be less predictable and more difficult to control. DeepSeek's technique innovates by using RL in a reasoning-oriented manner, making it possible for the model to learn reliable internal thinking with only very little process annotation - a technique that has shown promising in spite of its intricacy.

Q3: Did DeepSeek utilize test-time compute techniques similar to those of OpenAI?

A: DeepSeek R1's style emphasizes efficiency by leveraging strategies such as the mixture-of-experts technique, which activates only a subset of parameters, to decrease calculate during inference. This focus on efficiency is main to its expense advantages.

Q4: What is the difference between R1-Zero and R1?

A: R1-Zero is the initial design that finds out thinking solely through support learning without explicit process guidance. It generates intermediate reasoning steps that, while in some cases raw or combined in language, work as the foundation for knowing. DeepSeek R1, on the other hand, improves these outputs through human post-processing and monitored fine-tuning. In essence, R1-Zero offers the unsupervised "trigger," and R1 is the polished, more meaningful version.

Q5: How can one remain updated with thorough, technical research while managing a busy schedule?

A: Remaining current includes a combination 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, and getting involved in conversation groups and newsletters. Continuous engagement with online neighborhoods and collaborative research projects likewise plays an essential role in keeping up with technical developments.

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

A: The short response is that it's prematurely to tell. DeepSeek R1's strength, however, depends on its robust thinking abilities and its performance. It is especially well matched for tasks that need proven 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 and enterprise settings.

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

A: The open-source and affordable design of DeepSeek R1 reduces the entry barrier for deploying advanced language models. Enterprises and start-ups can take advantage of its sophisticated reasoning for agentic applications varying from automated code generation and client support to data analysis. Its versatile deployment options-on customer hardware for smaller sized models or cloud platforms for bigger ones-make it an attractive option to proprietary services.

Q8: Will the model get stuck in a loop of "overthinking" if no appropriate answer is found?

A: While DeepSeek R1 has actually been observed to "overthink" basic problems by checking out several thinking courses, it includes stopping criteria and examination mechanisms to avoid boundless loops. The reinforcement discovering structure encourages merging towards a verifiable output, even in uncertain cases.

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

A: Yes, DeepSeek V3 is open source and functioned as the foundation for later versions. It is built on its own set of innovations-including the mixture-of-experts approach and FP8 training-and is not based upon the Qwen architecture. Its style emphasizes efficiency and expense decrease, setting the phase for the thinking developments seen in R1.

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

A: DeepSeek R1 is a text-based model and does not incorporate vision abilities. Its design and training focus solely on language processing and thinking.

Q11: Can specialists in specialized fields (for example, labs dealing with remedies) apply these methods to train domain-specific models?

A: Yes. The innovations behind DeepSeek R1-such as its outcome-based reasoning training and effective architecture-can be adapted to different domains. Researchers in fields like biomedical sciences can tailor these methods to develop designs that address their specific obstacles while gaining from lower compute costs and robust thinking capabilities. It is most likely that in deeply specialized fields, nevertheless, there will still be a need for monitored fine-tuning to get dependable results.

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

A: The discussion showed that the annotators mainly concentrated on domains where accuracy is quickly verifiable-such as mathematics and coding. This suggests that knowledge in technical fields was certainly leveraged to make sure the accuracy and clearness of the thinking data.

Q13: Could the model get things incorrect if it counts on its own outputs for finding out?

A: While the design is created to enhance for right responses through reinforcement knowing, there is always a danger of errors-especially in uncertain scenarios. However, by assessing multiple prospect outputs and enhancing those that lead to proven results, the training process minimizes the possibility of propagating incorrect thinking.

Q14: How are hallucinations lessened in the model provided its iterative reasoning loops?

A: The use of rule-based, verifiable jobs (such as mathematics and coding) helps anchor the model's thinking. By comparing numerous outputs and utilizing group relative policy optimization to reinforce just those that yield the right result, the model is directed away from producing unfounded or hallucinated details.

Q15: Does the design rely 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 enable efficient thinking rather than showcasing mathematical complexity for its own sake.

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

A: Early iterations like R1-Zero did produce raw and sometimes hard-to-read reasoning. However, the subsequent refinement process-where human experts curated and improved the thinking data-has significantly boosted the clearness and dependability of DeepSeek R1's internal idea procedure. While it remains an evolving system, iterative training and feedback have resulted in significant improvements.

Q17: Which model versions appropriate for regional deployment on a laptop with 32GB of RAM?

A: For local testing, a medium-sized model-typically in the variety of 7B to 8B parameters-is recommended. Larger models (for example, those with hundreds of billions of parameters) need substantially more computational resources and are much better matched for cloud-based deployment.

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

A: DeepSeek R1 is provided with open weights, implying that its model criteria are openly available. This lines up with the overall open-source approach, enabling researchers and developers to more check out 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 existing technique permits the model to initially explore and create its own thinking patterns through not being watched RL, and after that improve these patterns with supervised methods. Reversing the order might constrain the design's capability to discover diverse reasoning courses, possibly limiting its general efficiency in tasks that gain from self-governing idea.

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

Assignee
Assign to
None
Milestone
None
Assign milestone
Time tracking
None
Due date
None
0
Labels
None
Assign labels
  • View project labels
Reference: alexandraoakle/vitricongty#1