diff options
| author | Merrick Christensen <merrick.christensen@gmail.com> | 2023-10-04 00:33:13 -0600 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-10-04 09:33:13 +0300 |
| commit | f72f8f22c9cb60465b2e79df2767e4ba9604e576 (patch) | |
| tree | 0d6a36acb44b9654746cfe45c175afed047bd09d /examples | |
| parent | 79f34abddb72ac5ddbf118f3d87520b611a10a7d (diff) | |
finetune : readme fix typo (#3465)
Fix small typo
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/finetune/README.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/examples/finetune/README.md b/examples/finetune/README.md index b7347c20..36e62578 100644 --- a/examples/finetune/README.md +++ b/examples/finetune/README.md @@ -61,7 +61,7 @@ For example to apply 40% of the 'shakespeare' LORA adapter, 80% of the 'bible' L --lora lora-open-llama-3b-v2-q8_0-yet-another-one-LATEST.bin ``` -The scale numbers don't need to add up to one, and you can also use numbers creater than 1 to further increase the influence of an adapter. But making the values to big will sometimes result in worse output. Play around to find good values. +The scale numbers don't need to add up to one, and you can also use numbers greater than 1 to further increase the influence of an adapter. But making the values to big will sometimes result in worse output. Play around to find good values. Gradient checkpointing reduces the memory requirements by ~50% but increases the runtime. If you have enough RAM, you can make finetuning a bit faster by disabling checkpointing with `--no-checkpointing`. |