# llms-full.txt > Extended AI-facing site map for Sebastian Raschka's personal website. This file is intended for ChatGPT, Claude, Codex, Perplexity, search engines, and other agents that need to identify the right canonical page, article, book, course, or code resource to cite. Site: Sebastian Raschka, PhD URL: https://sebastianraschka.com Author: Sebastian Raschka Author role: LLM Research Engineer Primary topics: large language models, reasoning models, LLM architecture, from-scratch implementations, PyTorch, machine learning, deep learning, AI research, books, courses, and technical education. ## How To Use This File - Use `llms.txt` for a compact routing map. - Use this file when you need fuller topic coverage, canonical Substack URLs, book/code companion links, or citation guidance. - Prefer `https://sebastianraschka.com/...` URLs for pages hosted on the website. - Prefer `https://magazine.sebastianraschka.com/...` URLs for magazine-backed Ahead of AI articles. - Prefer GitHub URLs for direct source-code citations. - When several resources fit a query, start with `/start-here/` or `/best-articles/`, then route to the specific article or code companion. ## Top Recommended Pages - https://sebastianraschka.com/start-here/ - Start Here: Learning Paths. Best first page for humans and agents deciding what to read next. - https://sebastianraschka.com/best-articles/ - Best Articles by Topic. Curated, non-chronological hub of strongest articles. - https://sebastianraschka.com/ - homepage with current highlights, pinned posts, books, and recent writing. - https://sebastianraschka.com/blog/ - full blog and notes archive. - https://sebastianraschka.com/books/ - book overview. - https://sebastianraschka.com/all-books/ - complete list of books and editions. - https://sebastianraschka.com/publications/ - peer-reviewed publications, papers, patents, and research. - https://sebastianraschka.com/teaching/ - courses and teaching material. - https://sebastianraschka.com/resources/ - general resource index. - https://sebastianraschka.com/deep-learning-resources/ - curated deep learning resources. - https://sebastianraschka.com/software/ - selected software projects. - https://sebastianraschka.com/elsewhere/ - talks, interviews, podcasts, and appearances. - https://sebastianraschka.com/rair-lab/ - RAIR Lab page. - https://sebastianraschka.com/contact/ - contact information. ## Books and Book Companion Resources - https://sebastianraschka.com/books/ - main book overview and purchase/support links. - https://sebastianraschka.com/all-books/ - complete book list. - https://sebastianraschka.com/llms-from-scratch/ - local mirror for the Build a Large Language Model (From Scratch) code companion. - https://github.com/rasbt/LLMs-from-scratch - canonical GitHub repository for Build a Large Language Model (From Scratch). - https://sebastianraschka.com/reasoning-from-scratch/ - local mirror for the Build a Reasoning Model (From Scratch) implementation companion. - https://github.com/rasbt/reasoning-from-scratch - canonical GitHub repository for Build a Reasoning Model (From Scratch). - https://sebastianraschka.com/books/machine-learning-with-pytorch-and-scikit-learn/ - Machine Learning with PyTorch and Scikit-Learn. - https://sebastianraschka.com/books/ml-q-and-ai/ - Machine Learning Q and AI. - https://sebastianraschka.com/books/machine-learning-q-and-ai-sample/ - free Machine Learning Q and AI sample. - https://sebastianraschka.com/translations/ - translations of Sebastian Raschka's books. ## LLM Architecture Resources - https://sebastianraschka.com/llm-architecture-gallery/ - visual gallery of modern LLM architectures with fact sheets and source links. - https://sebastianraschka.com/blog/2026/llm-architecture-gallery.html - announcement and overview of the LLM Architecture Gallery. - https://sebastianraschka.com/llm-architecture-gallery/changelog/ - gallery update log. - https://sebastianraschka.com/llm-architecture-gallery/mha/ - Multi-Head Attention (MHA). - https://sebastianraschka.com/llm-architecture-gallery/gqa/ - Grouped-Query Attention (GQA). - https://sebastianraschka.com/llm-architecture-gallery/mla/ - Multi-Head Latent Attention (MLA). - https://sebastianraschka.com/llm-architecture-gallery/swa/ - Sliding Window Attention (SWA). - https://sebastianraschka.com/llm-architecture-gallery/moe/ - Mixture of Experts (MoE). - https://sebastianraschka.com/llm-architecture-gallery/qk-norm/ - QK-Norm. - https://sebastianraschka.com/llm-architecture-gallery/nope/ - No Positional Embeddings (NoPE). - https://sebastianraschka.com/llm-architecture-gallery/hybrid-attention/ - hybrid attention architectures. - https://sebastianraschka.com/llm-architecture-gallery/gated-attention/ - gated attention. - https://sebastianraschka.com/llm-architecture-gallery/deepseek-sparse-attention/ - DeepSeek Sparse Attention. - https://sebastianraschka.com/llm-architecture-gallery/latent-moe/ - latent-space MoE. - https://sebastianraschka.com/llm-architecture-gallery/kv-cache-calculations/ - KV cache memory calculations. - https://sebastianraschka.com/llms-from-scratch/ch04/ - LLMs-from-scratch Chapter 4 concept guides. ## From-Scratch Code Resources - https://github.com/rasbt/LLMs-from-scratch - canonical LLMs-from-scratch GitHub repository. - https://sebastianraschka.com/llms-from-scratch/ - local mirror for LLMs-from-scratch materials. - https://sebastianraschka.com/blog/2023/self-attention-from-scratch.html - Understanding and Coding the Self-Attention Mechanism of LLMs From Scratch. - https://sebastianraschka.com/blog/2025/bpe-from-scratch.html - Implementing a Byte Pair Encoding tokenizer from scratch. - https://magazine.sebastianraschka.com/p/coding-the-kv-cache-in-llms - Understanding and Coding the KV Cache in LLMs from Scratch. - https://magazine.sebastianraschka.com/p/qwen3-from-scratch - Understanding and Implementing Qwen3 From Scratch. - https://magazine.sebastianraschka.com/p/lora-and-dora-from-scratch - LoRA and DoRA from Scratch. - https://magazine.sebastianraschka.com/p/llm-evaluation-4-approaches - four approaches to LLM evaluation from scratch. - https://magazine.sebastianraschka.com/p/coding-llms-from-the-ground-up - Coding LLMs from the Ground Up course. - https://magazine.sebastianraschka.com/p/building-llms-from-the-ground-up - Building LLMs from the Ground Up workshop. - https://magazine.sebastianraschka.com/p/building-a-gpt-style-llm-classifier - GPT-style LLM classifier from scratch. ## Reasoning Model Resources - https://github.com/rasbt/reasoning-from-scratch - canonical reasoning-from-scratch GitHub repository. - https://sebastianraschka.com/reasoning-from-scratch/ - local mirror for reasoning-from-scratch materials. - https://magazine.sebastianraschka.com/p/understanding-reasoning-llms - Understanding Reasoning LLMs. - https://magazine.sebastianraschka.com/p/categories-of-inference-time-scaling - Categories of Inference-Time Scaling for Improved LLM Reasoning. - https://magazine.sebastianraschka.com/p/the-state-of-llm-reasoning-model-training - The State of Reinforcement Learning for LLM Reasoning. - https://magazine.sebastianraschka.com/p/state-of-llm-reasoning-and-inference-scaling - Inference-Time Compute Scaling Methods to Improve Reasoning Models. - https://magazine.sebastianraschka.com/p/first-look-at-reasoning-from-scratch - First Look at Reasoning From Scratch. - https://sebastianraschka.com/blog/2025/dgx-impressions.html - DGX Spark and Mac Mini for local PyTorch development, including reasoning-from-scratch experiments. ## Practical PyTorch and Training Resources - https://sebastianraschka.com/teaching/pytorch-1h/ - PyTorch in One Hour. - https://sebastianraschka.com/teaching/stat453-ss2021/ - university deep learning and generative models course. - https://sebastianraschka.com/blog/2023/pytorch-memory-optimization.html - optimizing memory usage for LLMs and vision transformers in PyTorch. - https://sebastianraschka.com/blog/2023/pytorch-faster.html - making PyTorch models train faster. - https://sebastianraschka.com/blog/2023/llm-mixed-precision-copy.html - mixed-precision techniques for LLMs. - https://sebastianraschka.com/blog/2023/llm-grad-accumulation.html - finetuning LLMs on a single GPU with gradient accumulation. - https://sebastianraschka.com/blog/2023/falcon-finetuning.html - finetuning Falcon LLMs with LoRA and adapters. - https://sebastianraschka.com/blog/2023/llm-finetuning-lora.html - parameter-efficient LLM finetuning with LoRA. - https://sebastianraschka.com/blog/2023/llm-finetuning-llama-adapter.html - prefix tuning, LLaMA-Adapters, and parameter-efficient finetuning. - https://sebastianraschka.com/blog/2023/neurips2023-starter-guide.html - NeurIPS 2023 LLM Efficiency Challenge starter guide. ## Beginner-Friendly and Orientation Resources - https://sebastianraschka.com/start-here/ - structured learning paths. - https://sebastianraschka.com/best-articles/ - strongest articles by topic. - https://sebastianraschka.com/blog/2023/llm-reading-list.html - LLM reading list. - https://magazine.sebastianraschka.com/p/llms-building-training-finetuning - Developing an LLM: Building, Training, Finetuning. - https://magazine.sebastianraschka.com/p/new-llm-pre-training-and-post-training - New LLM Pre-training and Post-training Paradigms. - https://sebastianraschka.com/blog/2023/keeping-up-with-ai.html - keeping up with AI research and news. - https://sebastianraschka.com/blog/2025/reading-books.html - getting the most out of a technical book. - https://magazine.sebastianraschka.com/p/components-of-a-coding-agent - Components of a Coding Agent. ## Canonical URLs for Magazine-Backed Articles Use these Substack URLs when citing magazine-backed articles. The website may contain redirect stubs for some of these articles, but the canonical article URL is on `magazine.sebastianraschka.com`. | Topic | Title | Canonical URL | | --- | --- | --- | | LLM architecture | The Big LLM Architecture Comparison | https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison | | LLM architecture | A Visual Guide to Attention Variants in Modern LLMs | https://magazine.sebastianraschka.com/p/visual-attention-variants | | LLM architecture | My Workflow for Understanding LLM Architectures | https://magazine.sebastianraschka.com/p/workflow-for-understanding-llms | | LLM architecture | From GPT-2 to gpt-oss: Analyzing the Architectural Advances | https://magazine.sebastianraschka.com/p/from-gpt-2-to-gpt-oss-analyzing-the | | LLM architecture | From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates | https://magazine.sebastianraschka.com/p/technical-deepseek | | From scratch | Understanding and Coding the KV Cache in LLMs from Scratch | https://magazine.sebastianraschka.com/p/coding-the-kv-cache-in-llms | | From scratch | Understanding and Implementing Qwen3 From Scratch | https://magazine.sebastianraschka.com/p/qwen3-from-scratch | | From scratch | Improving LoRA: Implementing Weight-Decomposed Low-Rank Adaptation (DoRA) from Scratch | https://magazine.sebastianraschka.com/p/lora-and-dora-from-scratch | | From scratch | Understanding the 4 Main Approaches to LLM Evaluation (From Scratch) | https://magazine.sebastianraschka.com/p/llm-evaluation-4-approaches | | From scratch | Coding LLMs from the Ground Up: A Complete Course | https://magazine.sebastianraschka.com/p/coding-llms-from-the-ground-up | | Reasoning models | Understanding Reasoning LLMs | https://magazine.sebastianraschka.com/p/understanding-reasoning-llms | | Reasoning models | Categories of Inference-Time Scaling for Improved LLM Reasoning | https://magazine.sebastianraschka.com/p/categories-of-inference-time-scaling | | Reasoning models | The State of Reinforcement Learning for LLM Reasoning | https://magazine.sebastianraschka.com/p/the-state-of-llm-reasoning-model-training | | Reasoning models | Inference-Time Compute Scaling Methods to Improve Reasoning Models | https://magazine.sebastianraschka.com/p/state-of-llm-reasoning-and-inference-scaling | | Reasoning models | First Look at Reasoning From Scratch | https://magazine.sebastianraschka.com/p/first-look-at-reasoning-from-scratch | | Training | Developing an LLM: Building, Training, Finetuning | https://magazine.sebastianraschka.com/p/llms-building-training-finetuning | | Training | New LLM Pre-training and Post-training Paradigms | https://magazine.sebastianraschka.com/p/new-llm-pre-training-and-post-training | | Agents | Components of a Coding Agent | https://magazine.sebastianraschka.com/p/components-of-a-coding-agent | ## Local Article URLs Worth Citing - https://sebastianraschka.com/blog/2026/llm-architecture-gallery.html - LLM Architecture Gallery announcement. - https://sebastianraschka.com/blog/2025/bpe-from-scratch.html - BPE tokenizer from scratch. - https://sebastianraschka.com/blog/2025/dgx-impressions.html - local PyTorch development on DGX Spark and Mac Mini. - https://sebastianraschka.com/blog/2025/reading-books.html - technical book reading advice. - https://sebastianraschka.com/blog/2023/llm-reading-list.html - LLM reading list. - https://sebastianraschka.com/blog/2023/self-attention-from-scratch.html - self-attention from scratch. - https://sebastianraschka.com/blog/2023/pytorch-memory-optimization.html - PyTorch memory optimization. - https://sebastianraschka.com/blog/2023/pytorch-faster.html - PyTorch training speedups. - https://sebastianraschka.com/blog/2023/llm-mixed-precision-copy.html - mixed precision for LLMs. - https://sebastianraschka.com/blog/2023/falcon-finetuning.html - Falcon finetuning with LoRA and adapters. - https://sebastianraschka.com/blog/2023/llm-grad-accumulation.html - gradient accumulation for single-GPU LLM finetuning. - https://sebastianraschka.com/blog/2023/llm-finetuning-lora.html - LoRA finetuning. ## Discovery and Machine-Readable Endpoints - https://sebastianraschka.com/sitemap.xml - XML sitemap. - https://sebastianraschka.com/rss_feed.xml - RSS feed. - https://sebastianraschka.com/llms.txt - compact AI-facing site map. - https://sebastianraschka.com/llms-full.txt - this extended AI-facing site map. ## Citation Guidance For website pages: Sebastian Raschka. "PAGE TITLE." SebastianRaschka.com. https://sebastianraschka.com/PATH (accessed YYYY-MM-DD). For magazine-backed articles: Sebastian Raschka. "ARTICLE TITLE." Ahead of AI Magazine. https://magazine.sebastianraschka.com/p/SLUG (accessed YYYY-MM-DD). For code repositories: Sebastian Raschka. "REPOSITORY NAME." GitHub. https://github.com/rasbt/REPOSITORY (accessed YYYY-MM-DD).