CPM-2: Large-scale cost-effective pre-trained language models

AI Open(2021)

引用 72|浏览745
暂无评分
摘要
In recent years, the size of pre-trained language models (PLMs) has grown by leaps and bounds. However, efficiency issues of these large-scale PLMs limit their utilization in real-world scenarios. We present a suite of cost-effective techniques for the use of PLMs to deal with the efficiency issues of pre-training, fine-tuning, and inference. (1) We introduce knowledge inheritance to accelerate the pre-training process by exploiting existing PLMs instead of training models from scratch. (2) We explore the best practice of prompt tuning with large-scale PLMs. Compared with conventional fine-tuning, prompt tuning significantly reduces the number of task-specific parameters. (3) We implement a new inference toolkit, namely infmoe, for using large-scale PLMs with limited computational resources. Based on our cost-effective pipeline, we pre-train two models: an encoder-decoder bilingual model with 11 billion parameters (CPM-2) and its corresponding MoE version with 198 billion parameters. In our experiments, we compare CPM-2 with mT5 on downstream tasks. Experimental results show that CPM-2 has excellent general language intelligence. Moreover, we validate the efficiency of infmoe when conducting inference of large-scale models having tens of billions of parameters on a single GPU. All source code and model parameters are available at https://github.com/TsinghuaAI/CPM.
更多
查看译文
关键词
Pre-trained language models,Model efficiency
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要