References: Run a model in a few lines

Source material

Source curriculum (structural mirror, cited as further study):
• Hugging Face, "LLM Course", Chapter 2: "Using Transformers"
  Authors: the Hugging Face team (Lewis Tunstall, Leandro von Werra,
    Lysandre Debut, Sylvain Gugger, Merve Noyan, and others)
  Course page: https://huggingface.co/learn/llm-course/chapter2
  Code and notebooks: https://github.com/huggingface/course
  License: Apache 2.0 (prose and code)
  Required attribution: "Based on the Hugging Face LLM Course
    (huggingface.co/learn/llm-course), © Hugging Face, used under the
    Apache 2.0 license. This is an independent structural mirror;
    Hugging Face does not endorse it."
This lesson mirrors the structure of Chapter 2 (the pipeline() function,
behind the pipeline, the model and tokenizer APIs, and the Auto classes).
Clawdemy's lessons are original prose that follows the pedagogical arc of
the course. We do not reproduce or transcribe the course; we cite it as the
recommended companion. Course materials are used under the Apache 2.0 license
with the attribution above, which requires a link to the license and an
indication of changes, and does not permit implying endorsement.

Read this next

• Hugging Face LLM Course, Chapter 2: Using Transformers. The chapter this lesson mirrors. It goes a step further than we do on batching, padding, and the high-level tokenizer() call, all of which build on the three steps you ran here.

Going deeper

A short, durable list. Each link is a specific next step, not a generic pile.

• The transformers Quicktour. The official docs version of this lesson. The fastest reference when you forget which task string or which AutoModelFor<Task> class you need.

• Pipelines API reference. The full list of supported tasks and the arguments each pipeline accepts. Worth a scan so you know what the one-liner can do before you reach for the Auto classes.

• The Hugging Face Hub model browser. Filter by task and you will see the checkpoint names you pass to from_pretrained. Reading a few model cards makes the pipeline(model="...") override concrete.

Adjacent topics

Where this connects inside the track.

• What transformers do (lesson 1). The working picture (tokens in, tokens out, three shapes) that the three steps here make concrete: the tokenizer produces the tokens, the model is the shape, the head produces the output.

• Fine-tune a pretrained model on your own data (lesson 3). The next lesson stops using models as-is and starts changing them. It works at exactly this lower level (tokenizer, model, training loop), which is why opening the box here mattered.