DeepGraphLearning / GearNet

GearNet and Geometric Pretraining Methods for Protein Structure Representation Learning, ICLR'2023 (https://arxiv.org/abs/2203.06125)
MIT License
263 stars 27 forks source link

How to Fine-Tune My Pretrained Model on Downstream Tasks #67

Closed fourier20laplace closed 1 month ago

fourier20laplace commented 2 months ago

I currently have a LoRA fine-tuned ESM-3b model and want to evaluate its performance on the downstream task of EC number prediction. How should I modify the YAML file and related code? 如何使用我的预训练模型在下游任务上微调 我现在有一个lora微调后的ESM-3b模型,希望检测其在EC数预测这一下游任务的指标,我该如何修改yaml文件及相关的代码 scrshot