Update README.md

README.md

@@ -2,6 +2,7 @@
 license: mit
 datasets:
 - tuandunghcmut/normal_dataset
+- tuandunghcmut/coding-mcq-reasoning
 language:
 - en
 base_model:
@@ -14,13 +15,13 @@ pipeline_tag: text-generation
 
 *   This document provides guidance on getting started with `tuandunghcmut/Qwen25_Coder_MultipleChoice`, a model fine-tuned for multiple-choice coding questions.
 
-*   Future plans include refactoring the project into a well-structured GitHub repository, expanding the dataset, and retraining the model using distributed training for improved scalability.
-
 *   A demonstration notebook is available on Google Colab (click the badge below). Please note that the training code has been omitted from this notebook. It is intended solely for testing and inference using the latest checkpoint.
     [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://drive.google.com/file/d/1Q4jtRjIkFWIAM82pAg4OBPCLjpQ8ndpI/view?usp=sharing)
 
 *   Note: The Qwen2.5 Coder 1.5B-Instruct model might be too small for this task, and the current training dataset may be insufficient. Future iterations will explore using a larger model and more extensive data. However, the current model successfully adheres to the desired YAML format and demonstrates structured reasoning.
 
+*   Apologies for the current state of the project. The initial version has some inconsistencies, but future plans include refactoring the code into a more structured format, expanding the dataset, and retraining the model using distributed training for improved scalability. Additionally, we plan to train on a larger, high-quality dataset to enhance performance and ensure better stability.
+
 *   The guide below provides an explanation of the code presented in the notebook.
 
 ## Installation
@@ -1243,4 +1244,4 @@ Contributions are welcome! Please feel free to submit a Pull Request.
 
 ## License
 
-This project is licensed under the MIT License - see the LICENSE file for details.
+This project is licensed under the MIT License - see the LICENSE file for details.