Use the ChatGLM-6B model to train your own dataset
This project implements the fine-tuning of the ChatGLM-6B model based on P-Tuning v2. P-Tuning v2 reduces the amount of parameters that need to be fine-tuned to 0.1% of the original, and through methods such as model quantization and Gradient Checkpoint, it only needs a minimum of 7GB of video memory to run.
The following uses the ADGEN (advertising generation) data set as an example to introduce how to use the code.
Use ChatGLM-6B to train your own dataset
1. Install software dependencies
## 运行微调需要4.27.1版本的