Updated documentation for docs/source/reward_trainer.mdx to import th…

…e correct Enum for the reward modelling LoRA config (#1092)
huggingface · Dec 15, 2023 · 8140129 · 8140129
1 parent 48b3ef0
commit 8140129
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/docs/source/reward_trainer.mdx b/docs/source/reward_trainer.mdx
@@ -29,7 +29,7 @@ You should pass an `AutoModelForSequenceClassification` model to the [`RewardTra
 Just pass a `peft_config` in the keyword arguments of [`RewardTrainer`], and the trainer should automatically take care of converting the model into a PEFT model!
 
 ```python
-from peft import LoraConfig, task_type
+from peft import LoraConfig, TaskType
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 from trl import RewardTrainer, RewardConfig