openai/grok

4,259

stars

5

commits

Python

primary language

Mar 19, 2024

updated

README

OpenAI Grok Curve Experiments

Paper

This is the code for the paper Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets by Alethea Power, Yuri Burda, Harri Edwards, Igor Babuschkin, and Vedant Misra

Installation and Training

pip install -e .
./scripts/train.py

Contributors

2 commits

2 commits

1 commits

Similar repos

danielmamay/grokking

Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic…

44

ironjr/grokfast

Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"

582

huangjj2002/GLAM

0

matt-seb-ho/gfn_ntp

9

OSU-NLP-Group/GrokkedTransformer

Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to…

242

LaVi-Lab/FTTT

[ACL 2025] Official code for ''Learning to Reason from Feedback at Test-Time''.

13

huggingface/open-r1

Fully open reproduction of DeepSeek-R1

26,451

abacaj/train-with-fsdp

93

Languages

Python

98.2%

Jupyter Notebook

1.4%

openai/grok

4,259

stars

5

commits

Python

primary language

Mar 19, 2024

updated

README

OpenAI Grok Curve Experiments

Paper

This is the code for the paper Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets by Alethea Power, Yuri Burda, Harri Edwards, Igor Babuschkin, and Vedant Misra

Installation and Training

pip install -e .
./scripts/train.py

Similar repos

danielmamay/grokking

Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic…

44

ironjr/grokfast

Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"

582

huangjj2002/GLAM

0

matt-seb-ho/gfn_ntp

9

OSU-NLP-Group/GrokkedTransformer

Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to…

242

LaVi-Lab/FTTT

[ACL 2025] Official code for ''Learning to Reason from Feedback at Test-Time''.

13

huggingface/open-r1

Fully open reproduction of DeepSeek-R1

26,451

abacaj/train-with-fsdp

93

Contributors

2 commits

2 commits

1 commits

Languages

Python

98.2%

Jupyter Notebook

1.4%