added kro dataset schema to README.md

README.md

@@ -20,3 +20,20 @@ This repository hosts the development of an automated RLHF platform for Hugging
 A community-driven project to enhance Vision-Language Models (VLMs) for student-focused tasks.
 Leverages feedback from users and automated RLHF pipelines to continuously improve model performance and usability.
 
+
+
+# Dataset Schema for Project
+
+## KTO Dataset Structure
+
+The dataset should be organized into two splits: `train` and `test`.
+
+Each split contains the following features:
+
+| **Feature**   | **Type**  | **Description**                                                                      |
+|---------------|-----------|--------------------------------------------------------------------------------------|
+| `prompt`      | `string`  | The input text for the model. This should be a natural language query or input.      |
+| `completion`  | `string`  | The output text generated by the model in response to the `prompt`.                  |
+| `label`       | `bool`    | A binary value (`True` or `False`) indicating whether the `completion` is desirable. |
+
+