BramVanroy / fietje-2
An open, efficient LLM for Dutch
☆39Updated last week
Alternatives and similar repositories for fietje-2:
Users that are interested in fietje-2 are comparing it to the libraries listed below
- GEITje 7B: een groot open Nederlands taalmodel☆120Updated last month
- Evaluation of language models on mono- or multilingual tasks.☆76Updated this week
- AfroLID, a powerful neural toolkit for African languages identification which covers 517 African languages.☆30Updated last year
- OpusCleaner is a web interface that helps you select, clean and schedule your data for training machine translation models.☆50Updated this week
- SpaCyEx allows the creation of spaCy Matcher patterns with RegEx like syntax.☆58Updated 8 months ago
- A library for working with prompt templates locally or on the Hugging Face Hub.☆36Updated this week
- A collection of datasets for language model pretraining including scripts for downloading, preprocesssing, and sampling.☆56Updated 5 months ago
- Repository containing the code for training the CroissantLLM☆21Updated 11 months ago
- [EMNLP'23] Official Code for "FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models"☆29Updated 3 months ago
- A list of awesome open source projects in the machine learning field, who's developers are mainly based in Germany☆42Updated 4 months ago
- A collection of Italian benchmarks for LLM evaluation☆26Updated last month
- Efficiently find the best-suited language model (LM) for your NLP task☆111Updated last week
- A spaCy wrapper for GliNER☆101Updated 6 months ago
- A repository containing the code for translating popular LLM benchmarks to German.☆25Updated last year
- A Python library aimed at dissecting and augmenting NER training data.☆57Updated last year
- Norwegian Transformer Model☆115Updated last month
- A spaCy custom component that extracts and normalizes temporal expressions☆52Updated last year
- Library for pruning experts per language pair in NLLB-200☆31Updated last year
- ☆106Updated last year
- Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.☆77Updated 4 months ago
- Lightweight self-hosted span annotation tool☆24Updated this week
- Language Identification with Support for More Than 2000 Labels -- EMNLP 2023☆110Updated last month
- ☆195Updated 7 months ago
- negate_sentence(A Python module that doesn't negate sentences.)☆27Updated 3 months ago
- ☆29Updated 3 months ago
- Agile reading group that works☆13Updated 2 years ago
- Repository for the EM German Model☆104Updated last year
- The website of the Oscar Project☆11Updated last year
- MAFAND-MT☆55Updated 6 months ago