原书出处
Designing Large Language Model Applications
lookback ratio, defined as the ratio of the attention weights on the context tokens to the attention weights on the newly generated tokens. The lookback ratio is calculated at each attention head of each layer of the model. These ratios are used as features to train a linear classifier model.
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch08.html
EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf