dbmdz/berts
DBMDZ BERT, DistilBERT, ELECTRA, GPT-2 and ConvBERT models
This project offers specialized language models for tasks like text analysis and natural language understanding across various languages including German, Italian, Turkish, French, Dutch, and Ukrainian. It takes raw text in one of these languages and outputs a numerical representation that can be used for tasks like identifying names, places, or sentiment. Researchers, data scientists, and language technology developers can use these models to improve the accuracy of their applications.
159 stars. No commits in the last 6 months.
Use this if you are building an AI application that needs to understand and process text in German, Italian, Turkish, or other supported European languages, especially for historical texts.
Not ideal if your primary language of interest is not covered by the available models or if you require TensorFlow checkpoints.
Stars
159
Forks
12
Language
—
License
MIT
Category
Last pushed
Dec 06, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/dbmdz/berts"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Tongjilibo/bert4torch
An elegent pytorch implement of transformers
nyu-mll/jiant
jiant is an nlp toolkit
lonePatient/TorchBlocks
A PyTorch-based toolkit for natural language processing
monologg/JointBERT
Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"
grammarly/gector
Official implementation of the papers "GECToR – Grammatical Error Correction: Tag, Not Rewrite"...