Kirill-Kravtsov/drophead-pytorch

An implementation of drophead regularization for pytorch transformers

38
/ 100
Emerging

This project helps machine learning engineers improve the performance and generalization of their Transformer-based natural language processing models. By applying a regularization technique called DropHead, it takes an existing Hugging Face Transformer model (like BERT or RoBERTa) and outputs a more robust version that is less prone to overfitting, especially on smaller datasets. It's for machine learning engineers and researchers who are developing and fine-tuning NLP models for various tasks.

No commits in the last 6 months.

Use this if you are a machine learning engineer working with Hugging Face Transformer models and need to improve their stability and reduce overfitting during training.

Not ideal if you are not using PyTorch or Hugging Face Transformers, or if you need a pre-built solution that includes scheduled DropHead functionality out-of-the-box.

natural-language-processing deep-learning model-training machine-learning-engineering transformer-models
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

19

Forks

6

Language

Python

License

MIT

Last pushed

Aug 24, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Kirill-Kravtsov/drophead-pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.