recurrent-pretraining

Repository facts

Stars

981

Forks

89

Open issues and pull requests

1

Primary language

Python

License

Apache License 2.0 (Apache-2.0)

Owner

seal-rg · Organization

Created

Feb 7, 2025

Last push

Dec 29, 2025

Topics

• llms
• pretraining
• reasoning
• recurrent-depth

Rank #6,187 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Related projects

Projects that share this one’s GitHub topics.

• 6,948

  Rank 6,948: madaan/self-refine

  LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.

  822 starsPythonApache-2.0Last push Oct 4, 2024

• 9,277

  Rank 9,277: NVlabs/QeRL

  [ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.

  525 starsPythonApache-2.0Last push Mar 30, 2026

• 1,402

  Rank 1,402: PySpur-Dev/pyspur

  A visual playground for agentic workflows: Iterate over your agents 10x faster

  5,791 starsTypeScriptApache-2.0Last push Jun 29, 2026

• 1,483

  Rank 1,483: rasbt/reasoning-from-scratch

  Implement a reasoning LLM in PyTorch from scratch, step by step

  5,425 starsJupyter NotebookApache-2.0Last push Oct 2, 2026

• 1,786

  Rank 1,786: microsoft/LMOps

  General technology for enabling AI capabilities w/ LLMs and MLLMs

  4,484 starsPythonMITLast push Sep 15, 2026

• 3,006

  Rank 3,006: OFA-Sys/OFA

  Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

  2,553 starsPythonApache-2.0Last push Apr 24, 2024