# lam-data-cleaning

**Repository Path**: zjgemi/lam-data-cleaning

## Basic Information

- **Project Name**: lam-data-cleaning
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: LGPL-3.0
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-01-25
- **Last Updated**: 2024-01-25

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# lam-data-cleaning

This project is to reduce the number of samples required for training a large atomic model (LAM) developed based on the cloud-native workflow framework [dflow](https://github.com/deepmodeling/dflow). So far, [DeePMD](https://github.com/deepmodeling/deepmd-kit), [OCP](https://github.com/Open-Catalyst-Project/ocp) and [Nequip](https://github.com/mir-group/nequip) are supported.

## Installation

Install this project by

```
pip install .
```

Configure workflow server required by dflow before submit a workflow by command line

```
dpclean submit input.json
```

Some example input files can be found in [examples](examples/).