This project focuses on fine-tuning and evaluating the Llama 3 1.8B model on Amazon Bedrock for summarization tasks. It includes data preparation, model customization, and evaluation steps.

• 01_setup.ipynb: Initial setup notebook.
• 02_fine-tune_and_evaluate_llama31_8B_bedrock_summarization.ipynb: Notebook for fine-tuning and evaluation.
• 03_cleanup.ipynb: Cleanup notebook.
• Step01-DataPreparation.ipynb: Data preparation notebook.
• Step02-Customization.ipynb: Customization notebook.

[Provide instructions on how to run the notebooks and any other relevant scripts. Include example commands if applicable. For example:

1. Open the notebooks in JupyterLab or a similar environment.
2. Run the cells in the notebooks in the specified order.
3. Adjust parameters as needed. ]

1. Clone the repository:

   git clone https://github.com/QsingularityAi/Fine-tune-meta-llama-aws.git
   cd fine-tune-meta-llama-aws

2. Install dependencies:

   pip install -r requirements.txt

   (Create a requirements.txt file with the necessary packages if one doesn't exist.)

3. Configure AWS credentials:

   Configure your AWS credentials using the AWS CLI or by setting environment variables.

4. [Optional] Install JupyterLab:

   pip install jupyterlab