HerBERT
Polish NLP model
A BERT-based language model pre-trained on Polish corpora for understanding Polish language.
HerBERT is a BERT-based Language Model trained on Polish Corpora using only MLM objective with dynamic masking of whole words.
65 stars
7 watching
5 forks
last commit: almost 3 years ago
Linked from 1 awesome list
Related projects:
Repository | Description | Stars |
---|---|---|
dbmdz/berts | Provides pre-trained language models for natural language processing tasks | 155 |
kldarek/polbert | A Polish BERT-based language model trained on various corpora for natural language processing tasks | 70 |
langboat/mengzi | Develops lightweight yet powerful pre-trained models for natural language processing tasks | 533 |
sdadas/polish-nlp-resources | Pre-trained models and resources for Natural Language Processing in Polish | 329 |
ermlab/politbert | Trains a language model using a RoBERTa architecture on high-quality Polish text data | 33 |
certainlyio/nordic_bert | Provides pre-trained BERT models for Nordic languages with limited training data. | 164 |
tonianelope/multilingual-bert | Investigating multilingual language models for Named Entity Recognition in German and English | 14 |
turkunlp/wikibert | Provides pre-trained language models derived from Wikipedia texts for natural language processing tasks | 34 |
laurentmazare/ocaml-bert | Implementing BERT-like NLP models in OCaml using PyTorch bindings and pre-trained weights from popular sources. | 24 |
deeppavlov/slavic-bert-ner | A shared BERT model for NER tasks in Slavic languages, pre-trained on Bulgarian, Czech, Polish, and Russian texts. | 73 |
allenai/scibert | A BERT model trained on scientific text for natural language processing tasks | 1,532 |
dfki-nlp/gevalm | Evaluates German transformer language models with syntactic agreement tests | 7 |
zhuiyitechnology/pretrained-models | A collection of pre-trained language models for natural language processing tasks | 989 |
ymcui/pert | Develops a pre-trained language model to learn semantic knowledge from permuted text without mask labels | 356 |
tal-tech/edu-bert | A pre-trained language model designed to improve natural language processing tasks in education | 186 |