This commit is contained in:
Daniel Strobusch
2023-12-21 23:17:11 +01:00
committed by GitHub
parent e1d0c254d6
commit e7b7c4fa92

View File

@@ -134,7 +134,7 @@ Note other keys will be ignored by the loader.
## Memory Issues
Fine-tuning a large model with LoRA requires a machine with a deccent amount
Fine-tuning a large model with LoRA requires a machine with a decent amount
of memory. Here are some tips to reduce memory use should you need to do so:
1. Try using a smaller batch size with `--batch-size`. The default is `4` so