jaketae/ensemble-transformers
Ensembling Hugging Face transformers made easy
This project helps machine learning practitioners combine the predictions of several pre-trained transformer models, like those from Hugging Face, into a single, more robust prediction. You provide a list of existing transformer models, and it outputs a combined prediction that often performs better than any single model. This is useful for anyone building or deploying natural language processing or computer vision applications who wants to improve model accuracy and reliability.
No commits in the last 6 months. Available on PyPI.
Use this if you need to boost the performance and reliability of your existing transformer-based models for tasks like text classification or image recognition.
Not ideal if you are looking to train a single, entirely new model from scratch or if you need to combine models across different data types (e.g., text and images).
Stars
61
Forks
5
Language
Python
License
MIT
Category
Last pushed
Dec 24, 2022
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jaketae/ensemble-transformers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lvapeab/nmt-keras
Neural Machine Translation with Keras
dair-ai/Transformers-Recipe
🧠A study guide to learn about Transformers
SirawitC/Transformer_from_scratch_pytorch
Build a transformer model from scratch using pytorch to understand its inner workings and gain...
lof310/transformer
PyTorch implementation of the current SOTA Transformer. Configurable, efficient, and...
L-Zhe/FasySeq
A fast and easy implementation of Transformer with PyTorch.