GLM
2000년 도입 · 논문 46편에서 사용
GLM is a bilingual (English and Chinese) pre-trained transformer-based language model that follow the traditional architecture of decoder-only autoregressive language modeling. It leverages autoregressive blank infilling as its training objective.
출처: GLM-130B: An Open Bilingual Pre-trained Model
소개 논문: GLM-130B: An Open Bilingual Pre-trained Model
Language Models · Natural Language Processing