{"slug": "correction-for-listing-6-5-in-build-a-reasoning-model-from-scratch", "title": "Correction for Listing 6.5 in Build a Reasoning Model From Scratch", "summary": "Sebastian Raschka issued a correction for Listing 6.5 in his book 'Build a Reasoning Model From Scratch', changing the line 'torch.manual_seed(0)' to 'torch.manual_seed(5)' on page 198. The change is needed to reproduce the generated response and log-probability outputs in Chapter 6; the fix will be included in the next printing.", "body_md": "# Correction for Listing 6.5 in Build a Reasoning Model From Scratch\n\nThanks everyone for all the kind words and feedback. Super happy that you are enjoying *Build a Reasoning Model (From Scratch)*!\n\nUnfortunately, there’s a small typo in Listing 6.5 on page 198 (see the video below). The line `torch.manual_seed(0)`\n\nshould be `torch.manual_seed(5)`\n\n.\n\nThis is a tiny change, but it’s needed to reproduce the generated response in Listing 6.5 and the corresponding log-probability outputs later in Chapter 6. If you use 0, the code is of course still correct but the numeric results may be a bit different, which could be confusing. Anyway, it should be a small 1 character change :).\n\nThis will be fixed in the next printing.\n\nI am sorry about the oversight, and I hope this note saves you some debugging time.\n\nSource: lightly edited website version of my [Substack note](https://substack.com/@rasbt/note/c-301484736).\n\n## Read Next\n\n[LLMs From Scratch Reaches 100,000 GitHub Stars Short note celebrating the LLMs-from-scratch repository passing 100,000 GitHub stars and summarizing its learning materials.](/blog/2026/llms-from-scratch-reaches-100000-github-stars.html)\n\n[Kimi K3 Architecture Notes Short architecture note on Kimi K3, including LatentMoE, Kimi Delta Attention, Attention Residuals, NoPE, multimodality, and inference-efficiency choices.](/blog/2026/kimi-k3-architecture-notes.html)\n\n[A Few Notable Open-Weight Models This Week Short note on the architectures of six new open-weight models, including Nanbeige 4.2, Laguna S 2.1, Motif-3-Beta, Solar Open 2, Antares 1B, and BTL-3.](/blog/2026/notable-open-weight-models-this-week.html)", "url": "https://wpnews.pro/news/correction-for-listing-6-5-in-build-a-reasoning-model-from-scratch", "canonical_source": "https://sebastianraschka.com/blog/2026/reasoning-model-listing-6-5-correction.html", "published_at": "2026-07-25 08:18:12+00:00", "updated_at": "2026-08-09 11:45:43.018494+00:00", "lang": "en", "topics": ["large-language-models", "ai-research"], "entities": ["Sebastian Raschka", "Build a Reasoning Model From Scratch"], "alternates": {"html": "https://wpnews.pro/news/correction-for-listing-6-5-in-build-a-reasoning-model-from-scratch", "markdown": "https://wpnews.pro/news/correction-for-listing-6-5-in-build-a-reasoning-model-from-scratch.md", "text": "https://wpnews.pro/news/correction-for-listing-6-5-in-build-a-reasoning-model-from-scratch.txt", "jsonld": "https://wpnews.pro/news/correction-for-listing-6-5-in-build-a-reasoning-model-from-scratch.jsonld"}}