我要如何获得预测文件呢

[LDLINGLINGLING]

Prerequisites

Before submitting your question, please ensure the following:

• I am running the latest version of PowerInfer. Development is rapid, and as of now, there are no tagged versions.
• I have carefully read and followed the instructions in the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).

Question Details

我如果需要对模型进行训练后再使用powerinfer，那如何获得预测文件呢，是否有这种方法

Additional Context

Please provide any additional information that may be relevant to your question, such as specific system configurations, environment details, or any other context that could be helpful in addressing your inquiry.

[LDLINGLINGLING]

Now openbmb has open sourced a sparse model, including pytorch version and gguf version, of which gguf can be directly inferred in powerinfer. I use llamacpp to convert the pytorch model into gguf. At this time, the gguf model cannot be inferred by powerinfer. Is there a way to solve it? All in all, my question is if I have a pytorch sparse model, how to convert it into a gguf model that powerinfer can use