Find and run heavyweight models from the Hub, debug runs, and drive a decoder — GPT-2, sampling, chat models, and a chatbot.
A beginner-friendly guide to the Hugging Face Hub — how to find the right model and read its card and license — plus how to run large models with quantization so they fit on a free Colab GPU.
A practical debugging playbook for beginner PyTorch and Hugging Face inference: missing packages, CUDA availability, device mismatch, shape errors, OOM, gated models, preprocessing mistakes, and slow first runs.
The other half of the transformer family: the decoder. A beginner-friendly look at how GPT-2 generates text — next-token prediction, the autoregressive loop, and running it in three lines — building on the encoder you already read.
A beginner-friendly guide to decoding and sampling in text generation — greedy vs sampling, temperature, top-k, top-p, and repetition penalty — the handful of knobs that turn robotic or unhinged output into something good.
Why GPT-2 rambles and ChatGPT answers: a beginner-friendly look at instruction-tuned and chat models — base vs instruct, chat templates with system and user roles, and running a small chat model on a free GPU.
The grand finale: wrap a small instruction-tuned model in a real chat interface with Gradio — system prompt, conversation memory, and a public link — then look back at everything the Running Models series taught you.