File size: 185 Bytes
0c6ac33 |
1 2 3 4 5 6 7 8 |
---
tags:
- fp8
---
Made with https://github.com/neuralmagic/AutoFP8:
```
python quantize.py --model-id facebook/opt-125m --save-dir opt-125m-fp8-dynamic --activation-scheme dynamic
``` |