Update README.md

README.md

@@ -54,43 +54,5 @@ print(output)
 Training the Model
 The training process involves loading the pre-trained BART model and tokenizer, preparing a custom dataset, and training the model using the PyTorch DataLoader. Refer to the train_model() and evaluate_model() functions in the code for the detailed implementation.
 
-Saving and Uploading the Model
-After training, save your model and tokenizer using:
-
-# Save the model and tokenizer
-save_directory = "./custom_bart_model"
-custom_model.model.save_pretrained(save_directory)
-tokenizer.save_pretrained(save_directory)
-Upload the saved model to Hugging Face Hub:
-
-
-from huggingface_hub import notebook_login, create_repo, upload_folder
-
-# Log in to Hugging Face
-notebook_login()
-
-# Upload to Hugging Face Hub
-upload_folder(
-    folder_path=save_directory,
-    path_in_repo="",
-    repo_id="your_hf_username/custom-bart-finetuned",
-    repo_type="model",
-)
-Generating Summaries
-The model can be used to generate summaries by feeding it input text. Adjust the parameters in the generate_summary() function to tweak the length, beam size, and other settings.
-
-Contributing
-Contributions are welcome! If you have any suggestions or improvements, please submit a pull request.
-
-License
-This project is licensed under the MIT License - see the LICENSE file for details.
-
-
-### Key Points:
-- **Overview**: Describes what the project is about.
-- **Installation**: Lists dependencies and how to install them.
-- **Usage**: Provides instructions on how to load and use the model.
-- **Training, Saving, and Uploading**: Steps to train, save, and upload the model.
-- **Contributing and License**: Information on contributing and licensing.
 
 Feel free to modify any section to better fit your project’s needs!