— series
LLMs
5 articles
- 01
From Transformer to LLMs
This article explores the evolution from Transformers to Large Language Models (LLMs), detailing the mechanisms of self-attention and multi-head attention, the role of position embeddings, various types of transformer models, and the training and fine-tuning processes of LLMs.
Read article → - 02
Preference Alignment: RLHF and DPO
An in-depth exploration of preference alignment techniques for LLMs, including Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO).
Read article → - 03
LLM-based Agents: Single and Multi-Agent Systems
Overview of LLM-based agents, including single-agent and multi-agent systems, core components (planning, memory, tool use), and common coordination and planning patterns.
Read article → - 04
LLMs in LangChain - Part 1. Conceptual
This article provides an overview of Large Language Models (LLMs), LLMs evolution and the core concepts of LangChain - an open source framework for building applications based on LLMs.
Read article → - 05
LLMs in LangChain - Part 2. LLMs Core Concepts
This article provides an overview of the core concepts of Large Language Models (LLMs) in LangChain, including LLM components, prompt templates, indexing, memory, chains, and agents.
Read article →