Rijgersberg / GEITje
GEITje 7B: een groot open Nederlands taalmodel
☆116Updated 3 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for GEITje
- Evaluation of language models on mono- or multilingual tasks.☆75Updated last week
- An open, efficient LLM for Dutch☆35Updated 2 months ago
- A Scandinavian Benchmark for sentence embeddings☆28Updated last week
- Norwegian Transformer Model☆114Updated this week
- A project for training foundational Danish language model☆68Updated this week
- Repository for the EM German Model☆104Updated last year
- Use machine learning to make your institutional communication more understandable and inclusive.☆40Updated 2 months ago
- Sentiment Corpus for Swedish 🇸🇪 Norwegian 🇳🇴 Danish 🇩🇰 Finnish 🇫🇮 (and English 🏴)☆15Updated 3 years ago
- ☆68Updated 8 months ago
- Norwegian Speech Transformer Models☆17Updated last week
- Simply, faster, sentence-transformers☆140Updated 2 months ago
- Semantic search engine indexing 95 million academic publications☆76Updated this week
- 📜 Dehyphenation of broken text (mainly German), i.e., extracted from a PDF☆38Updated 2 years ago
- 💥 Use Hugging Face text and token classification pipelines directly in spaCy☆62Updated 8 months ago
- 💭 Retrieval augmented generation (RAG) and language model powered search applications☆279Updated 10 months ago
- A spaCy wrapper for GliNER☆91Updated 4 months ago
- 🗺️ Data Cleaning and Textual Data Visualization 🗺️☆146Updated 5 months ago
- Python bindings for the Tweede Kamer OData API☆16Updated last year
- Libraries, Archives and Museums (LAM)☆82Updated 2 years ago
- 📚 Process PDFs, Word documents and more with spaCy☆75Updated this week
- The official repository for Toxic Commons and Celadon. Toxicity Classification for public domain data.☆9Updated last week
- A BERT-based application for reusable text classification at scale☆37Updated last year
- Various training, inference and validation code and results related to Open LLM's that were pretrained (full or partially) on the Dutch l…☆27Updated 7 months ago
- A Dutch RoBERTa-based language model☆197Updated 7 months ago
- A repository of instructions in French to fine-tune LLMs☆17Updated last year
- An easy way to chunk spaCy docs.☆16Updated 3 months ago
- Projekt «Named Entity Recognition für die zentralen Serien des Staatsarchivs Kanton Zürich»☆9Updated last month
- 📚 Datasets and models for instruction-tuning☆233Updated last year
- An EUR-Lex parser for Python.☆28Updated 4 months ago
- BERTje is a Dutch pre-trained BERT model developed at the University of Groningen. (EMNLP Findings 2020) "What’s so special about BERT’s …☆135Updated last year