In this repository the MDZ Digital Library team (dbmdz) at the Bavarian State
Library open sources another German BERT models 🎉
German BERT
Stats
In addition to the recently released
German BERT
model by
deepset
we provide another German-language model.
The source data for the model consists of a recent Wikipedia dump, EU Bookshop corpus,
Open Subtitles, CommonCrawl, ParaCrawl and News Crawl. This results in a dataset with
a size of 16GB and 2,350,234,427 tokens.
For sentence splitting, we use
spacy
. Our preprocessing steps
(sentence piece model for vocab generation) follow those used for training
SciBERT
. The model is trained with an initial
sequence length of 512 subwords and was performed for 1.5M steps.
This release includes both cased and uncased models.
Model weights
Currently only PyTorch-
Transformers
compatible weights are available. If you need access to TensorFlow checkpoints,
please raise an issue!
bert-base-german-cased huggingface.co is an AI model on huggingface.co that provides bert-base-german-cased's model effect (), which can be used instantly with this dbmdz bert-base-german-cased model. huggingface.co supports a free trial of the bert-base-german-cased model, and also provides paid use of the bert-base-german-cased. Support call bert-base-german-cased model through api, including Node.js, Python, http.
bert-base-german-cased huggingface.co is an online trial and call api platform, which integrates bert-base-german-cased's modeling effects, including api services, and provides a free online trial of bert-base-german-cased, you can try bert-base-german-cased online for free by clicking the link below.
dbmdz bert-base-german-cased online free url in huggingface.co:
bert-base-german-cased is an open source model from GitHub that offers a free installation service, and any user can find bert-base-german-cased on GitHub to install. At the same time, huggingface.co provides the effect of bert-base-german-cased install, users can directly use bert-base-german-cased installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
bert-base-german-cased install url in huggingface.co: