Am1n3e/active-learning-transformer
A hands-on tutorial on how to use Active Learning with Transformer models.
This project helps machine learning practitioners efficiently train powerful Transformer models for text classification tasks. By strategically selecting the most informative data points for labeling, you can achieve high model performance with less manually labeled data. It takes in an unlabeled text dataset and outputs a trained Transformer model with optimized performance for tasks like sentiment analysis or spam detection.
No commits in the last 6 months.
Use this if you need to train a high-performing text classification model but have limited resources for manual data labeling.
Not ideal if your task is not text classification, or if you already have a very large, well-labeled dataset.
Stars
15
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 03, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Am1n3e/active-learning-transformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/transformers-bloom-inference
Fast Inference Solutions for BLOOM
Tencent/TurboTransformers
a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc)...
mit-han-lab/lite-transformer
[ICLR 2020] Lite Transformer with Long-Short Range Attention
mit-han-lab/hardware-aware-transformers
[ACL'20] HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
LibreTranslate/Locomotive
Toolkit for training/converting LibreTranslate compatible language models 🚂