Search

Noah Constant

SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer
ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models
The Power of Scale for Parameter-Efficient Prompt Tuning
nmT5: Is Parallel Data Still Relevant for Pre-training Massively Multilingual Language Models?
mT5: A massively multilingual pre-trained text-to-text transformer
LAReQA: Language-agnostic answer retrieval from a multilingual pool
Bridging the Gap for Tokenizer-Free Language Models
Character-Level Language Modeling with Deeper Self-Attention

Published with Wowchemy — the free, open source website builder that empowers creators.