# German NLP

LLäMmlein 7B is a German LLaMA language model with 7 billion parameters, trained from scratch on the German part of the RedPajama V2 dataset based on the adjusted Tinyllama codebase.

A German sentence transformer model fine-tuned based on the ESCO classification system, specifically designed for career matching and recommendation systems

BERT model pre-trained on UD_German-HDT for German POS tagging and dependency parsing

This is a German language model based on the GPT-2 architecture, specifically optimized for German text generation tasks.

A German RoBERTa model trained using the WECHSEL method, achieving cross-lingual transfer of monolingual language models through effective initialization of subword embeddings.

GottBERT is the first RoBERTa model specifically designed for German, pre-trained on the German portion of the OSCAR dataset, available in both base and large versions.

Large German language processing model provided by spaCy, supporting NLP tasks such as POS tagging, dependency parsing, and named entity recognition

CPU-optimized German processing pipeline including tokenization, part-of-speech tagging, morphological analysis, dependency parsing, lemmatization, named entity recognition, etc.

CPU-optimized German processing pipeline, including tokenization, POS tagging, morphological analysis, dependency parsing, lemmatization, named entity recognition, etc.

This is a lightweight BERT model optimized for German, retaining most of the original BERT model's performance through knowledge distillation while significantly reducing model size and computational requirements.

A German news text classification model fine-tuned from bert-base-german-cased, trained on the 10K GNAD dataset