Welcome to the repository that serves as a comprehensive guide for Machine Learning (ML) Engineer job interviews, with a focus on Large Language Models (LLMs). Here, you'll find detailed discussions and examples based on recent interview questions and topics I've encountered.
The repository is organized into several main sections, each dedicated to a specific aspect of LLMs:
- LLMs
- Metrics: Learn about the different metrics used to evaluate the performance of LLMs, including examples of how to calculate and interpret these metrics.
- Quantization: Explore the techniques and benefits of model quantization as a means to reduce model size and accelerate inference, complete with code examples.
- Fine-tuning: Understand the processes and best practices for fine-tuning pre-trained LLMs to specific tasks or datasets, including practical implementation guides.
- LLMs/metrics: Contains scripts and notebooks detailing how to measure and interpret the performance of LLMs using various metrics.
- LLMs/quantization: Includes examples and tutorials on how to apply quantization techniques to LLMs to optimize performance and efficiency.
- LLMs/fine_tuning: Provides resources and guides for fine-tuning LLMs, including example code and detailed explanations.
To get started with this repository, clone it locally and explore the topics that interest you:
git clone https://github.com/your-username/ml-interview-questions.git
cd ml-interview-questions
Contributions are welcome! If you have additional examples, corrections, or topics to add, please feel free to fork the repository and submit a pull request.
If you have any questions or want to discuss the topics further, feel free to reach out via GitHub or by emailing me at [email protected]