DPLM DPLM (diffusion protein language model) is a versatile protein language model that demonstrates strong generative and predictive capabilities for protein sequences. Specifically, DPLM exhibits impressive performance in protein sequence generation, motif scaffolding, inverse folding, and representation learning. For more detailed information about DPLM, please refer to our paper Diffusion Language Models Are Versatile Protein Learners. This repository contains the DPLM model checkpoint of 650M parameters. Please refer to our github repository for code and usage. For example, you can load DPLM model as below: All DPLM checkpoints are available in the table below: Model size Num layers Num parameters dplm 3b 36 3B dplm 650m 33 650M dplm 150m 30 150M News : welcome to check our new work DPLM 2: A Multimodal Diffusion Protein Language Model, a multimodal protein foundation model that extends DPLM to simultaneously model, understand, and generate both sequences and structures!
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy