Stefan Schweter

turkish-bert. Turkish BERT/DistilBERT, ELECTRA, ConvBERT and T5 models

capsnet-nlp. CapsNet for NLP

nmt-en-vi. Neural Machine Translation system for English to Vietnamese (IWSLT'15 English-Vietnamese data)

fine-tuned-berts-seq. Fine-tuned Transformers compatible BERT models for Sequence Tagging

europeana-bert. BERT and ELECTRA models trained on Europeana Newspapers

flair-experiments. Experiments with Zalando's flair library

german-gpt2. German GPT-2 model

modern-bert-ner. My NER Experiments with ModernBERT and Ettin

italian-bertelectra. 🇮🇹 Italian BERT and ELECTRA models (incl. evaluation)

dl-benchmarks. Deep Learning Benchmark Results (RTX 2080 TI vs. RTX 2070)

xlm-v-experiments. Experiments for XLM-V Transformers Integeration

gc4lm. GC4LM: A Colossal (Biased) language model for German

ukrainian-electra. Ukrainian ELECTRA model

hetzner-gpu-server. My cheatsheet for Hetzner GPU Server Setup

hmByT5. Upcoming Historical Multilingual and Monolingual ByT5 Models

lrz-gpu-tutorial. Useful tips for LRZ GPU usage

delpher-lm. Language Model for Historic Dutch (Delpher Corpus)

hmBench. hmBench: Fine-Tuning, Evaluating & Benchmarking of Historic Language Models on NER Datasets

flair-pos-tagging. Flair Embeddings for PoS Tagging: A Multilingual Evaluation

deep-wittgenstein. Classification of Wittgenstein's remarks

plur. Pre-trained Language Models for Under-represented Languages in NLP

nmt-mk-en. Neural Machine Translation system for Macedonian to English

hmTEAMS. Historical Multilingual TEAMS Models

germeval-ner-t5. Evaluating German T5 Models on GermEval 2014 (NER)

model-garden-lms. Language Model Pretraining with TensorFlow Model Garden

blbooks-lms. Pretrained Language Models on British Library Corpus

gerturax-fine-tuner. GERTuraX fine-tuning experiments

stefan-it.

transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

georgian-ner. Resources about Named Entity Recognition for Georgian

transformer-smaller-training-vocab. Temporary remove unused tokens during training to save ram and speed.

tecb-de. German Text Embedding Clustering Benchmark

FARM. :house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry.

historic-domain-adaptation-icdar. Data Centric DomainAdaptation for Historical Text with OCR Errors

co-funer. Experiments on CO-Fun NER Dataset

awesome-huggingface. 🤗 A list of wonderful open-source projects & applications integrated with Hugging Face libraries.

adapters. A Unified Library for Parameter-Efficient and Modular Transfer Learning