DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

1. DeepSeek-V3

   1 13 91,990 8.2 Python

   

2. CodeRabbit

   coderabbit.ai featured

   CodeRabbit: AI Code Reviews for Developers. Revolutionize your code reviews with AI. CodeRabbit offers PR summaries, code walkthroughs, 1-click suggestions, and AST-based analysis. Boost productivity and code quality across all major languages with each PR.

   

3. TinyZero

   2 9 11,174 9.4 Python

   Clean, minimal, accessible reproduction of DeepSeek R1-Zero

   

   >I wonder if this was a deliberate move by PRC or really our own fault in falling for the fallacy that more is always better.

   Well, let’s see …hmmm… are we discussing this on a platform ran by people who made insane money flipping zero-value companies to greater fools during the dotcom bubble, only to pivot to doing the same thing to big tech during the FANG era or one for discussing of hard ML research among the no-nonsense math elite from some of the world’s top universities.

   More seriously, we don’t have to even speculate about any of this because the methods from DeepSeek’s work are already being reproduced:

   https://github.com/Jiayi-Pan/TinyZero

4. open-r1

   3 4 22,804 9.4 Python

   Fully open reproduction of DeepSeek-R1

   

5. DeepSeek-LLM

   4 25 4,462 7.2 Makefile

   DeepSeek LLM: Let there be answers

   

   I've been using https://chat.deepseek.com/ over My ChatGPT Pro subscription because being able to read the thinking in the way they present it is just much much easier to "debut" - also I can see when it's bending it's reply to something, often softening it or pandering to me - I can just say "I saw in your thinking you should give this type of reply, don't do that". If it stays free and gets better that's going to be interesting for OpenAI.

6. LLMstudio

   5 2 315 9.6 Python

   Framework to bring LLM applications to production

   

   > And of course if you ask it anything related to the CCP it will suddenly turn into a Pinokkio simulator.

   Smh this isn't a "gotcha!". Guys, it's open source, you can run it on your own hardware[^2]. Additionally, you can liberate[^3] it or use an uncensored version[^0] on your own hardware. If you don't want to host it yourself, you can run it at https://nani.ooo/chat (Select "NaniSeek Uncensored"[^1]) or https://venice.ai/chat (select "DeepSeek R1")

   [^0]: https://huggingface.co/mradermacher/deepseek-r1-qwen-2.5-32B...

   [^1]: https://huggingface.co/NaniDAO/deepseek-r1-qwen-2.5-32B-abla...

   [^2]: https://github.com/TensorOpsAI/LLMStudio

   [^3]: https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in...

7. DeepSeek-R1

   6 28 86,634 7.6

   

   If you’re referring to what I think you’re referring to, those distilled models are from deepseek and not ollama https://github.com/deepseek-ai/DeepSeek-R1

8. hai-platform

   7 1 377 - Python

   一种任务级GPU算力分时调度的高性能深度学习训练平台

   

   it's open source, here is their platform called hai: https://github.com/HFAiLab/hai-platform

9. SaaSHub

   www.saashub.com featured

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

10. r2md

    8 1 8 8.2 Rust

    Convert an entire code repository (local or remote) to a single markdown or pdf file

    

    made this super easy to use tool https://github.com/skirdey-inflection/r2md

Suggest a related project