Open Reproduction of DeepSeek-R1

(github.com)

85 points | by yogthos 3 hours ago

7 comments

  • Tiberium 2 hours ago
    Last update over a year ago, so I hope (2025) gets added to the title:

    > [2025/05/26] (Step 1 completed!) We release Mixture-of-Thoughts--a curated reasoning dataset of 350k verified traces distilled from R1. The dataset spans tasks in mathematics, coding, and science, and is designed to teach language models to reason step-by-step. We also provide a recipe to train OpenR1-Distill-7B, which replicates the reasoning capabilities of deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and marks the completion of step 1 in the Open R1 project.

    Doesn't look like they managed to actually reproduce R1, and only stopped on Step 1 out of their 3-step plan.

    • spmurrayzzz 1 hour ago
      One of my favorite code comments of all time is still in the src:

      "# TODO: implement a proper validator to compare against ground truth. For now we just check for exact string match on each line of stdout." [1]

      This was one of my chief complaints about the entire R1 news cycle, it felt like no one actually read the technical report. They were being heralded for their openness, but they left out the most meaningful details that you'd need to reproduce their work.

      [1] https://github.com/huggingface/open-r1/blob/1416fa0cf21595d2...

      • neutronicus 1 hour ago
        Reminds me of my days in a computational physics PhD program.
  • aesthesia 1 hour ago
    If you really want to see fully open training pipelines for modern LLMs, Olmo and to a lesser extent Nemotron are what you should look at.

    https://github.com/allenai/OLMo

    https://github.com/NVIDIA-NeMo/Nemotron

    • spijdar 36 minutes ago
      I'm not really familiar with either, but I'm more familiar with Olmo. My impression is Nemotron is newer -- why is it less applicable? Is it not totally open like Olmo?
      • lambda 2 minutes ago
        Olmo releases their full datasets.

        Nemotron only releases portions of some of their datasets, like the source code dataset that they pretrain on.

        For example, from https://docs.nvidia.com/nemotron/latest/nemotron/super3/pret... :

          Open-source data coverage: The released datasets cover an estimated 8–10T tokens 
          (~40–50% of the internal 25T blend). Missing categories include code (~14% of blend), 
          nemotron-cc-code (~2%), crawl++ (~2%), and academic text (~2%). Users should 
          supplement with their own data for these categories and adjust train_iters 
          accordingly.
        
        K2 Think V2 is another fully open model like Olmo, with full datasets released.

        Note that the Nemotron models are generally stronger than Olmo and K2 Think V2 (according to Artificial Analysis benchmarks), and there is a lot of overlap in their datasets (lots of datasets are based on the same sources with different filtering, Olmo and K2 Think V2 both have used some Nemotron datasets).

  • madiator 2 hours ago
    Check out OpenThoughts. It has a widely used dataset, a model that beats the deepseek's smaller reasoning models, and a paper that talks in detail about the data curation methodology.

    https://www.open-thoughts.ai/

  • poppafuze 25 minutes ago
    "This will likely involve curating new, large-scale datasets for math, reasoning, and code.". ... everybody likes to hand-wave on this .
  • yieldcrv 1 hour ago
    Too old now
  • christkv 1 hour ago
    What is the estimated cost these days to train something like this to conclusion?
  • RedMagicBox 47 minutes ago
    [dead]