zero-shot
·19 words·1 min
Deeplearning
transformer
·81 words·1 min
self-attention mechanism
·49 words·1 min
GPT
·81 words·1 min
few-shot
·22 words·1 min
BERT
·39 words·1 min
Attention Is All You Need
·7 words·1 min
supervised fine-tuning
·23 words·1 min
preference tuning
·23 words·1 min