Data and model weights for a series of antibody language models

This repo contains the sequence dataset for finetuning and model weights including pre-trained meta model and a series of finetuned antibody language models. The antibody language models were used in the paper "Physics-driven structural docking and protein language models accelerate antibody screening and design for broad-spectrum antiviral therapy" for antibody sequence embedding.本仓库包含用于模型微调的序列数据集，以及各类模型权重，其中涵盖预训练元模型（pre-trained meta model）与一系列微调后的抗体语言模型（antibody language model）。 该系列抗体语言模型已在论文《物理驱动的结构对接与蛋白质语言模型加速广谱抗病毒治疗的抗体筛选与设计》中被用于抗体序列嵌入任务。