Skip to content

Releases: LonxunQuantum/PWMLFF

add nep cpu and gpu version of lammps

11 Sep 11:15
Compare
Choose a tag to compare

add nep cpu and gpu version of lammps

2024.3

14 Mar 06:34
Compare
Choose a tag to compare

Full Changelog: v0.1.0...2024.3

  1. Add DP compression method. (3rd and 5th-order polynomial)
  2. Introduce DP type embedding method. (DP model)
  3. Update to PyTorch 2 framework, and modify the network model to adapt to LibTorch. (DP model)
  4. Implement GPUMD and NEP.
  5. Calculate features on-the-fly.
  6. Integrate pwdata (a data conversion tool) for dataset extraction.
  7. Resolve bugs.
  8. ...

v0.1.0

11 Sep 09:22
Compare
Choose a tag to compare

Full Changelog: v0.0.2...v0.1.0

新增DP model 混合训练
新增自由选择是否使用含有atomic energy的数据集(MOVEMENT文件)
程序执行逻辑修改,用户输入现使用.json文件设置
新增NN model 及 Linear model在lammps计算中的virial的推理
新增推理接口,方便验证DFT结果与训练预测结果的正确性
修复Bug:
混合训练力场用于lammps计算时,原子顺序问题
DP model 训练时batch_size只能为特定数值的问题
NN model 训练无法更新Ei的问题
NN model 和 Linear model 特征保存时的精度问题导致*******
NN model 和 Linear model 调用进行evaluation时MOVEMENT的读取逻辑
使用力场进行lammps计算时,最大近邻数不适配问题
程序编译报错问题
多个MOVEMENT产生特征时内存泄漏问题
......

v0.0.2

08 Aug 06:36
Compare
Choose a tag to compare

Full Changelog: v0.0.1...v0.0.2

v0.0.1

21 Jul 05:05
Compare
Choose a tag to compare

First Release 🎉

What's Changed

Full Changelog: https://github.com/LonxunQuantum/PWMLFF/commits/v0.0.1