dbiir/UER-py

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

49
/ 100
Emerging

This tool helps machine learning engineers and researchers accelerate their natural language processing (NLP) projects. It allows you to take raw text data, feed it into existing pre-trained language models like BERT, or train new ones, and then adapt these models for specific tasks such as text classification or understanding. The output is a highly effective, specialized model ready for deployment in your NLP applications.

3,106 stars. No commits in the last 6 months.

Use this if you need to quickly build or customize state-of-the-art natural language processing models for tasks like sentiment analysis, question answering, or text generation, leveraging existing powerful pre-trained models.

Not ideal if you are working with multi-modal data (text and images, for example) or need to train extremely large language models with billions of parameters, in which case a newer version like TencentPretrain might be more suitable.

natural-language-processing machine-learning-engineering text-classification language-model-training sentiment-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

3,106

Forks

524

Language

Python

License

Apache-2.0

Last pushed

May 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/dbiir/UER-py"

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