This chapter provides a comprehensive overview of tools and techniques for programming large language models (LLMs), covering both fundamental and advanced aspects of their implementation. The first section explores different programming languages and frameworks, with a particular focus on Python due to its ecosystem of libraries, such as Hugging Face and LangChain, which facilitate model training, fine-tuning, and deployment. The chapter then presents a practical overview of pre-training and fine-tuning methodologies, discussing approaches like unsupervised and supervised learning, instruction tuning, parameter-efficient fine-tuning, and alignment fine-tuning to optimize LLM performance. In the final section, prompt engineering techniques are examined, including zero-shot, few-shot, and chain-of-thought prompting, demonstrating how structured prompts enhance model reasoning and response accuracy. Through examples and code snippets, the chapter offers a hands-on guide for understanding and exploiting LLMs efficiently, balancing computational resources, and improving task-specific performance.