OpenBMB stands for Open Lab for Big Model Base. It aims to build a large-scale pretrained language model library and related tools, accelerate the training, fine-tuning, and inference of large models with over ten billion parameters, lower the barrier to using large models, and work together with developers at home and abroad to form an open-source community for large models, promote the development of the large model ecosystem, realize the standardization, popularization, and practical application of large models, and bring large models into thousands of households.
The OpenBMB open-source community is jointly supported and initiated by the Natural Language Processing Laboratory of Tsinghua University and the Language Model Acceleration Technology Innovation Center of BAAI. The initiating team has a deep research foundation in natural language processing and pretrained models. In recent years, it has published dozens of high-level papers at top international conferences on model pretraining, prompt fine-tuning, model compression techniques, and other aspects.
