Contents Part 1 · Inference from zero
Part 1 · Inference from zero
Inside a Hugging Face model, file by file: the config, the tokenizer, the chat template, the safetensors bytes and the cache
Every file in a real model repository read with plain Python on a rented machine: each config.json field and where it matters later, the chat template rendered for a real message, the safetensors header byte by byte, sharded models, the Hugging Face cache, pinned revisions and gated models.
Code zip with this lesson
This lesson is part of the paid Inference Engineering course
The founding price is ₹2,222 or $99$49, one payment. It rises to ₹9,999 or $249 after the founding period, and buying now gives you every part as it is released, at no extra cost, with lifetime access.
Free to study first: Introduction: what this course builds, Before you start, Prefill and decode and The KV cache.
Already bought it? Sign in to read this lesson.