archinetai/smart-pytorch
PyTorch – SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models.
This project helps machine learning engineers or researchers fine-tune pre-trained language models more effectively. It takes an existing neural network and its input embeddings, and outputs a regularization loss that makes the model more robust. The end result is a language model that performs better and is less sensitive to small changes in input data.
No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer working with pre-trained language models and need to improve their robustness and generalization during fine-tuning.
Not ideal if you are looking for a general-purpose adversarial training library for computer vision or other domains outside of natural language processing.
Stars
62
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jun 28, 2022
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/archinetai/smart-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kk7nc/RMDL
RMDL: Random Multimodel Deep Learning for Classification
MaximeVandegar/Papers-in-100-Lines-of-Code
Implementation of papers in 100 lines of code.
OML-Team/open-metric-learning
Metric learning and retrieval pipelines, models and zoo.
miguelvr/dropblock
Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.
DLTK/DLTK
Deep Learning Toolkit for Medical Image Analysis