DPA-3.2-5M is trained using a multitask strategy on the OpenLAM datasets V2. Compared with DPA-3.1-3M, the following changes were made:

To use the pretrained model, you need to first install the corresponding version of DeePMD-kit. You can try easy installation:

For other installation options, please visit the Releases page page to download the off-line package for deepmd-kit devel, and refer to the official documentation for off-line installation instructions.

The pretrained model can be used directly for prediction tasks, such as serving as an ASE calculator.

This model is pretrained in a multi-task manner, featuring a unified backbone (referred to as the unified descriptor and the unified fitting net) and an dataset encoding vector for different tasks. For detailed information, refer to the DPA-3 paper.

The first step involves selecting a specific dataset id from the model to make predictions. To list the available fitting nets (model-branch) in this pretrained model, use the following command:

This will generate an output similar to the following:

Together with the available branch list, a table containing detailed information of each branch is provided. Select a model branch that closely matches your system. Ensure that the elements in your system are included in the corresponding task if you are conducting direct predictions or simulations. For more information on the pretrained datasets, refer to OpenLAM datasets V2.

*Note: If you are unsure which model branch to use, we recommend starting with Omat24, which performs well across a wide range of systems, including inorganic materials, catalytic systems, and molecular systems. If the accuracy of the Omat24 branch does not meet your needs for catalytic applications, consider trying the OC20M branch. For molecular systems, we recommend the OMol25 branch. For 2D inorganic materials, we recommend the Alex2D branch, and for inorganic materials under high pressure, the MPGen_OpenCSP branch. For alloy systems, we recommend the Alloy_APEX branch. *

Assuming you choose OMol25, you can first freeze the model branch from the multi-task pretrained model:

or use the alias like

Then you can use the following Python code for prediction or optimization:

Given that energy labels calculated via DFT can vary by an arbitrary constant, LAMs are consistently used to predict the energy difference between the label and a dummy model that estimates potential energy solely based on the chemical formula. Specifically, the dummy model is defined as

E = Σₑ nₑ · b̂ₑ;

where E is the predicted energy, nₑ is the number of atoms of element e, and b̂ₑ is the per-atom energy of element e obtained via least-squares fitting:

b̂ = argmin Σᵢ ( yᵢ − Σₑ nᵢ,ₑ bₑ )²,

with nᵢ,ₑ denoting the number of atoms of element e in sample i, and yᵢ the corresponding DFT energy label. When applying the pretrained model to a new downstream system, it is advisable to adjust the energy bias term to better align with the DFT energy labels of the downstream system. This adjustment can enhance prediction accuracy without necessitating further training of the neural network parameters.

To be specific, given a new downstream system, we use dp --pt change-bias to do zero-shot procedure, which will inherit the neural network parameters of the pretrained multitask model, but updating the energy bias to better align with the downstream system.

To fine-tune a pretrained model, you need to ensure that the model configuration (model/descriptor and model/fitting_net) matches exactly with the pretrained model. The input_finetune.json file provided on this page contains the same model configuration as the pretrained model.

To prepare for fine-tuning, replace the model/type_map and training/training(validation)_data sections in input_finetune.json with your specific dataset information, just the same as from scratch. Additionally, adjust the learning rate for fine-tuning, typically a small learning rate such as 1e-4 for learning_rate/start_lr is recommended. One can inherit a pretrained fitting net by using the --model-branch argument.