Pinned Repositories
AskLLM
Various tools for AskLLM
cite
Implementation for our paper "Conditional Image-Text Embedding Networks"
create-deuncase-dataset
DedupScandEval
DensitySampler
north-t5
Norwegian T5
pere-levanter
Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax
PlayWithWords
ttconnect
VACMA-PUBLIC
Publicly accessible files related to the VACMA project
peregilk's Repositories
peregilk/north-t5
Norwegian T5
peregilk/ttconnect
peregilk/PlayWithWords
peregilk/VACMA-PUBLIC
Publicly accessible files related to the VACMA project
peregilk/create-deuncase-dataset
peregilk/AskLLM
Various tools for AskLLM
peregilk/cite
Implementation for our paper "Conditional Image-Text Embedding Networks"
peregilk/DedupScandEval
peregilk/DensitySampler
peregilk/FlanScand
Flan translated to Scandinavian languages
peregilk/KeyBERT
Minimal keyword extraction with BERT
peregilk/norec_sentence
Aggregated datasets for sentence-level sentiment classification in Norwegian
peregilk/pere-levanter
Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax
peregilk/rotobart
Pre-training BART in Flax on The Pile dataset
peregilk/ScandEval
Evaluation of language models on mono- or multilingual Scandinavian language tasks.
peregilk/ScandEvalTsv
Clone of ScandEval dataset in tsv format
peregilk/distil-whisper
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
peregilk/maxtext-no-tools
peregilk/maxtextno
A simple, performant and scalable Jax LLM!
peregilk/me
Just personal, non sensitive stuff
peregilk/mlkurs
peregilk/NCC2_tools
peregilk/SimCSE
EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
peregilk/transformers
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
peregilk/unsupervised-video
[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
peregilk/voicecraft-tools
peregilk/whisperX
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
peregilk/WhisperXGPU
Transcribing the corpus with WhisperX