Slices

🐛 Bug Fixes | 问题修复
**修复了MatterGPT/eform/2_inverse_eform_novelty/workflow/script.py的自动清空结果的问题。**
Fixed the issue of automatic result clearing in MatterGPT/eform/2_inverse_eform_novelty/workflow/script.py.

🐛 Bug Fixes | 问题修复
Memory Leak Fix | 内存泄漏修复 🔄 Crystal Reconstruction Routine of MatterGPT | 晶体重建流程
修复MatterGPT晶体结构重建流程的TensorFlow 内存泄漏问题
大幅提高晶体重建成功率
优化m3gnet/chgnet优化过程中的内存管理
增强长时间运行的稳定性
Fixed TensorFlow memory leak in MatterGPT's Crystal Reconstruction Routine
Improved crystal reconstruction success rate
Optimized memory handling during tensor operations
Enhanced long-running process stability

1. 引入MatterGPT模型，这是一个基于GPT2的新材料大语言模型，专门为凝聚态材料逆向设计打造，擅长进行多性质逆向设计。详情请参阅 [[ 论文 ]](https://arxiv.org/abs/2408.07608)。新增三个Jupyter教程（2.1、2.2、2.3），方便用户快速上手逆向设计新材料。 添加了一个在线演示 [[材料大模型在线演示]](https://huggingface.co/spaces/xiaohang07/MatterGPT_CPU).
2. 更新SLI2Cry算法：将第三步的M3GNet IAP替换为CHGNet IAP，进一步提高可逆性，增强SLICES晶体解码能力。添加了一个在线演示 [[SLICES编解码在线演示]](https://huggingface.co/spaces/xiaohang07/SLICES). 可以在线对SLICES和CIF进行转换以及数据增广。
3. 将CrystalNN设置为SLICES编码使用的默认晶体化学键识别算法。
4. 采用SLICES strategy=4作为新的默认编码方法。这种编码可以缩短SLICES长度约40%，有效降低大模型的计算量。新型编码示例：
C C 0 1 ooo 0 1 +oo 0 1 o+o 0 1 oo+
这种方法将偏移矢量从三个独立的token简化为一个token，有效精简SLICES字符串。
5. 将新版本的代码文件放在slices文件夹中。调用SLICES库的命令从：
from invcryrep.invcryrep import InvCryRep
变为更加直观的：
from slices.core import SLICES
6. Docker镜像现在使用'python setup.py develop'安装/crystal/slices文件夹中的代码，方便进行SLICES算法的开发。用户可以直接在/crystal/slices中修改源代码，确保docker调用的SLICES库始终是最新版本，无需重新安装或配置环境。
7. DFT计算使用custodian进行自动化纠错，提高计算成功率。

We have developed new tutorials for SLICES based on Jupyter notebooks. This comprehensive overhaul makes the tutorials much easier to use. 🧠⛏️💎
<img width="1086" alt="Jupyter" src="https://github.com/xiaohang007/SLICES/assets/33337564/32f37cd5-4d2c-423e-abf4-3eb23d92271e">

Installing SLICES is now easier than ever with just one command: "**pip install slices**".

If you're in China and want to speed up the download, you can use this command instead: "pip install slices -i https://pypi.tuna.tsinghua.edu.cn/simple".

Please note that this installtion method is intended for Linux operating systems like Ubuntu and CentOS. Unfortunately, SLICES is not compatible with Windows due to the modified XTB binary was compiled on Linux.

Once the installation is complete, you can immediately explore SLICES' capabilities. Test the encoding/decoding and data augmentation/canonicalization functions using the *.py files located in the /examples directory. It's a quick and easy way to get started!