Skip to content

Removed duplicate sentence #265

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Removed duplicate sentence #265

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 1 addition & 3 deletions units/en/unit2/2.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,8 +111,6 @@ DPO requires a [preference dataset](https://huggingface.co/docs/trl/en/dataset_f

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 |
|-----------|-------------|-----------------|
| **Beta (β)** | Controls the strength of preference optimization | **Range**: 0.1 to 0.5<br>**Lower values**: More conservative, closer to reference model<br>**Higher values**: Stronger preference alignment, risk of overfitting |
Expand Down Expand Up @@ -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.