File size: 331 Bytes
68eafd2 e7d466f bda3cf5 |
1 2 3 4 5 6 7 8 9 10 |
---
license: apache-2.0
---
This project contains the onnx and tensorrt model files converted from the chatglm-6b model.
The infer scripts for onnx and tensorrt will be refined later
onnx2engine.py used to convert onnx into tensorrt engine, batch is now 1, can be modified
according to their own video memory into dynamic batch
|