<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Checkpoint on Zero to One AI</title><link>https://blog.crazyai.uk/tags/checkpoint/</link><description>Recent content in Checkpoint on Zero to One AI</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 22 Aug 2026 18:10:00 +0800</lastBuildDate><atom:link href="https://blog.crazyai.uk/tags/checkpoint/index.xml" rel="self" type="application/rss+xml"/><item><title>The Model File Has No Names</title><link>https://blog.crazyai.uk/posts/inference-field-notes-01-the-model-file-has-no-names/</link><pubDate>Sat, 22 Aug 2026 18:10:00 +0800</pubDate><guid>https://blog.crazyai.uk/posts/inference-field-notes-01-the-model-file-has-no-names/</guid><description>Following a TinyStories checkpoint from PyTorch export to mmap, KV cache, and token sampling in Karpathy&amp;#39;s llama2.c.</description></item><item><title>A Live Wire Is Not a Language</title><link>https://blog.crazyai.uk/posts/transformer-field-notes-04-live-wire-is-not-a-language/</link><pubDate>Thu, 20 Aug 2026 11:34:00 +0800</pubDate><guid>https://blog.crazyai.uk/posts/transformer-field-notes-04-live-wire-is-not-a-language/</guid><description>The model could memorize one batch, lower validation loss, restore a checkpoint, and imitate a play—without learning honest English.</description></item></channel></rss>