Scholarlink

This chapter is a practical introduction to post-training optimization and deployment of large language models (LLMs). Our primary focus will be on two crucial techniques: Retrieval-Augmented Generation (RAG) and fine-tuning, which are essential for enhancing LLM capabilities. We will explore the technical foundations of these methods and discuss the specific scenarios where each approach is most applicable. Next, we turn our attention to inference systems. We will explore the technical background of inference, including the computational processes involved and the metrics used to evaluate their performance. By the end of this chapter, you will have a better understanding of post-training optimization and inference for a deployed LLM.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Inference, Fine-Tuning, and Retrieval-Augmented Generation

  • 章节

  • 发表日期：

    2025年

查看全文
  • Vikram Dhillon,
  • David Metcalf,
  • Max Hooper

摘要

This chapter is a practical introduction to post-training optimization and deployment of large language models (LLMs). Our primary focus will be on two crucial techniques: Retrieval-Augmented Generation (RAG) and fine-tuning, which are essential for enhancing LLM capabilities. We will explore the technical foundations of these methods and discuss the specific scenarios where each approach is most applicable. Next, we turn our attention to inference systems. We will explore the technical background of inference, including the computational processes involved and the metrics used to evaluate their performance. By the end of this chapter, you will have a better understanding of post-training optimization and inference for a deployed LLM.