pere's repositories
VACMA-PUBLIC
Publicly accessible files related to the VACMA project
cite
Implementation for our paper "Conditional Image-Text Embedding Networks"
FlanScand
Flan translated to Scandinavian languages
KeyBERT
Minimal keyword extraction with BERT
norec_sentence
Aggregated datasets for sentence-level sentiment classification in Norwegian
pere-levanter
Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax
rotobart
Pre-training BART in Flax on The Pile dataset
ScandEval
Evaluation of language models on mono- or multilingual Scandinavian language tasks.
ScandEvalTsv
Clone of ScandEval dataset in tsv format
maxtextno
A simple, performant and scalable Jax LLM!
SimCSE
EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
transformers
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
unsupervised-video
[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
whisperX
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)