原书出处
Designing Large Language Model Applications
Attention with Linear Biases (ALiBi) In this technique, the attention scores are penalized with a bias term proportional to the distance between the query token and the key token. This technique also enables modeling sequences of longer length during inference than what was encountered in the training process. Rotary Position Embedding (RoPE) Just like ALiBi, this technique has the property of relative decay; there is
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/ch04.html
EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf