#pre-trained-model Repositories
Discover 10 active open source GitHub repositories tagged with #pre-trained-model, accumulating 35,819 total stars (averaging 3,581 stars per project). Leading this topic is microsoft/unilm with 22,247 stars.
10 repositories total
[ICLR'23 Spotlight๐ฅ] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention
[MICCAI 2019 Young Scientist Award] [MedIA Best Paper Award] Models Genesis: self-supervised pre-training for 3D medical images. Learns transferable representations from unlabeled CT and MRI volumes, then fine-tunes for downstream segmentation and classification. Keras and PyTorch weights included.
Self-supervised contrastive learning for time series via time-frequency consistency
Frequently Asked Questions
What is the most popular #pre-trained-model repository on GitHub?
The top ranked open source #pre-trained-model project on GitHub is microsoft/unilm with 22,247 stars. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Which programming languages are most used in #pre-trained-model repositories?
Among the top ranked #pre-trained-model projects on GitHub, the most common programming languages are Python, Jupyter Notebook.
How is the #pre-trained-model repository ranking calculated?
We track 10 active open source repositories tagged with #pre-trained-model (500+ stars), totaling 35,819 stars with an average of 3,581 stars per repository. Rankings update daily from the GitHub API.