Eliminate duplicate text chunk (#290)

Removed redundant sentence about prompt recommendations.

Author: Muscle-Oliver

units/en/unit2/2.md

@@ -109,8 +109,6 @@ trainer.train()
 
 DPO requires a [preference dataset](https://huggingface.co/docs/trl/en/dataset_formats#preference). The `DPOTrainer` supports both [conversational](https://huggingface.co/docs/trl/en/dataset_formats#conversational) and [standard](https://huggingface.co/docs/trl/en/dataset_formats#standard) dataset formats. When provided with a conversational dataset, the trainer will automatically apply the chat template to the dataset.
 
-Although the `DPOTrainer` supports both explicit and implicit prompts, we recommend using explicit prompts. If provided with an implicit prompt dataset, the trainer will automatically extract the prompt from the `"chosen"` and `"rejected"` columns. For more information, refer to the [preference style](dataset_formats#preference) section.
-
 Although the `DPOTrainer` supports both explicit and implicit prompts, we recommend using explicit prompts. If provided with an implicit prompt dataset, the trainer will automatically extract the prompt from the `"chosen"` and `"rejected"` columns. For more information, refer to the [preference style](https://huggingface.co/docs/trl/en/dataset_formats#preference) section.
 
 | Parameter | Description | Recommendations |
@@ -149,4 +147,4 @@ Another common issue is distribution shift, where the model performs well on the
 - Evaluating alignment quality and model performance
 - Deploying your aligned model
 
-After mastering DPO, explore advanced techniques in the [advanced DPO methods](3) section.
+After mastering DPO, explore advanced techniques in the [advanced DPO methods](3) section.