Start from a pretrained Deep Potential model, fine-tune it for your system, and deploy it at simulation scale.
Pretrained models · Fine-tuning · Documentation · Quick start · Model guide · Tutorials · Examples · Releases
Important
A pretrained model can be your starting point, not just your end result. Download a built-in DPA checkpoint, fine-tune the full model, or use a DPA-4 LoRA adapter with PyTorch single-task training, then test, export, and deploy it through the same DeePMD-kit workflow.
DeePMD-kit turns quantum-mechanical reference data into fast, scalable interatomic potentials. Use it across molecular and materials science—from finite molecules and covalent systems to periodic solids and metals—and scale from laptop fine-tuning to distributed training and MPI-parallel molecular dynamics.
The DPA4 model family traces a Pareto frontier across Matbench Discovery CPS and saturated inference throughput.
| Advantage | What it unlocks | |
|---|---|---|
| 🧬 | Pretrained-first workflows | Download pretrained DPA models, fine-tune full models, use DPA-4 LoRA adapters with PyTorch single-task training, or adapt learned representations to downstream properties with DPA-ADAPT. |
| 🏗️ | Training from scratch | Design a model for a new system or physical target, then train it with single-task, multi-task, and distributed workflows across supported backends. |
| 🧠 | Modern model portfolio | Start with efficient DeepPot-SE descriptors or move to DPA for large atomistic models. |
| 🧲 | More than energy and force | Model virials, Hessians, spin and magnetic forces, dipoles, polarizabilities, electronic density of states, atomic populations, and arbitrary intensive or extensive properties. |
| 🔄 | Backend flexibility | Train or run supported models with TensorFlow, PyTorch, JAX, or Paddle, with backend-aware model formats and conversion paths for compatible architectures. |
| 🚀 | Performance from training to MD | Use CPUs, CUDA GPUs, ROCm source builds, distributed training, model compression, compiled DPA-4 paths, AOTInductor .pt2 export, and MPI-enabled simulation. |
| 🔌 | Deploy where science happens | Use the CLI, Python, C, C++, or Node.js, then connect models to LAMMPS, i-PI, ASE, GROMACS, JAX MD, nvalchemi, OpenMM, Amber, CP2K, ABACUS, and more. |
| 🧩 | Open and extensible | Compose hybrid potentials, add analytical ZBL or long-range corrections, create custom models and operators, or connect external GNNs such as MACE and NequIP through plugins. |
Tip
On supported descriptors and workloads, model compression can deliver more than 10× inference speedup and reduce memory usage by as much as 20×. Actual gains depend on the model, system, and hardware.
Backend and interface support varies by model and feature. The web documentation marks compatibility and limitations on each feature page.
flowchart LR
A["Pretrained DPA model"] --> C["Fine-tune on target data"]
B["Model configuration"] --> D["Train from scratch"]
E["Target reference data"] --> C
E --> D
C --> F["Test, compress, export"]
D --> F
F --> G["Python and native APIs"]
F --> H["Molecular dynamics"]
- Choose a starting point: download a pretrained DPA checkpoint for adaptation, or configure a model to train from scratch.
- Prepare target data in DeePMD's NumPy format or convert structures and trajectories with dpdata.
- Fine-tune or train: adapt the full pretrained model, use DPA-4 LoRA adapters with PyTorch single-task training, or optimize a new model with single-task, multi-task, and distributed training workflows.
- Validate and export with
dp test,dp freeze, backend conversion, embedding extraction, and supported compression paths. - Run simulation through Python or native APIs, or load the model into a supported molecular-dynamics engine.
DeePMD-kit requires Python 3.10 or later. The fastest installation path is:
curl -fsSL https://dp1s.deepmodeling.com | bash
dp --version
dp -hThe installation guide covers pip, conda-forge, containers, offline packages, GPU builds, LAMMPS, i-PI, and source installation.
Download a built-in checkpoint, inspect its branches, and fine-tune the branch that matches your target system:
dp pretrained download DPA-3.2-5M
dp --pt show ~/.cache/deepmd/pretrained/models/DPA-3.2-5M.pt model-branch
dp --pt train input.json \
--finetune ~/.cache/deepmd/pretrained/models/DPA-3.2-5M.pt \
--model-branch <branch> \
--use-pretrain-scriptDPA-3.2-5M is a PyTorch multi-task checkpoint: run the trainer in PyTorch
mode with dp --pt and select the branch that matches your system with
--model-branch (list them with
dp --pt show ~/.cache/deepmd/pretrained/models/DPA-3.2-5M.pt model-branch). The
--use-pretrain-script option imports that branch's descriptor and fitting
configuration, so input.json does not need to reproduce the DPA-3.2
architecture.
The fine-tuning guide covers full-model adaptation. DPA-4 LoRA fine-tuning is available for PyTorch single-task training. DPA-ADAPT reuses pretrained DPA representations for downstream property-prediction tasks.
Pretrained model names can also be resolved and cached automatically by Python:
from deepmd.infer import DeepPot
potential = DeepPot("DPA-3.2-5M")Training from scratch remains a first-class workflow for new architectures, fully custom systems, and physical targets without a suitable pretrained checkpoint. Clone the examples and start with the compact water system:
git clone https://github.com/deepmodeling/deepmd-kit.git
cd deepmd-kit/examples/water/se_e2_a
# TensorFlow backend
dp train input.json
# Or PyTorch
dp --pt train input_torch.jsonReady-to-run inputs include:
For a guided end-to-end example, open the web quick-start notebook.
DeepPot-SE is a strong default: efficient, established, and broadly supported. For large atomistic models, start with DPA-4.
Use the model guide to compare model families, supported backends, targets, data formats, precision, compression, and deployment constraints.
DPA4 provides a family of accuracy–throughput trade-offs for different deployment budgets.
| Goal | DeePMD-kit capabilities |
|---|---|
| Potential-energy surfaces | Energy, atomic forces, virials, Hessians, hybrid descriptors, pair tables, and linear model combinations |
| Magnetic systems | Spin-aware descriptors, atomic and magnetic forces, and spin-capable molecular dynamics |
| Electronic and response properties | Dipoles, polarizabilities, density of states, atomic charge populations, and custom property heads |
| Long- and short-range physics | DPLR electrostatics, DPRc range correction for QM/MM, and analytical ZBL bridging |
| Representation learning | Per-atom descriptors, fitting-network features, structural embeddings, clustering, and downstream auxiliary models |
Explore the complete set of models and physical targets in the web documentation.
- LAMMPS, i-PI, ASE, JAX MD, and nvalchemi
- Ecosystem integrations for OpenMM, Amber, CP2K, GROMACS, ABACUS, DP-GEN, and MLatom
- External MACE and NequIP models through the DeePMD-GNN plugin
See the integration hub for maintained interfaces, third-party projects, supported scope, and installation guidance.
The native C and C++ interfaces load machine-learning backends as runtime plugins. Applications can therefore open the backend required by a model without directly linking every framework.
Note
Working with an AI coding or scientific agent? DeePMD-kit ships official Agent Skills for model selection, training, fine-tuning, Python inference, and LAMMPS workflows.
- Read the full web documentation.
- Follow hands-on material in the DeepModeling tutorials.
- Browse examples for training, inference, and integrations.
- Ask questions or report problems in GitHub Issues.
- Join development through the contributing guide.
If DeePMD-kit contributes to published work, cite the general software paper that matches the version used and the method-specific papers listed in CITATIONS.bib:
- Wang et al., “DeePMD-kit: A deep learning package for many-body potential
energy representation and molecular dynamics,” Computer Physics
Communications 228 (2018), 178–184 (describes the initial version).
- Zeng et al., “DeePMD-kit v2: A software package for Deep Potential models,”
The Journal of Chemical Physics 159 (2023), 054801 (covers features until
v2.2.3).
- Zeng et al., “DeePMD-kit v3: A Multiple-Backend Framework for Machine
Learning Potentials,” Journal of Chemical Theory and Computation 21
(2025), 4375–4385 (covers features until v3.0).
DeePMD-kit is licensed under the GNU Lesser General Public License v3.0 or later.