PPLM builds on top of other large transformer-based generative models (like GPT-2), where it enables finer-grained control of attributes of the generated language (e.g. gradually switching topic 🐱 or sentiment 😃).

⚠️ 🐍 We had to turn off the PPLM machine as it was costly to host – try it locally using transformers, or contact us if you really need it as a hosted service. 🐍 ⚠️ {{!-- Replace this text and hit tab to trigger generations. Have fun! --}}

See how a modern neural network auto-completes your text 🤗

{{!-- In February, OpenAI unveiled a language model called GPT-2 – for Generative Pre-Trained Transformer – that generates coherent paragraphs of text one word at a time. --}} This site, built by the Hugging Face team, lets you write a whole document directly from your browser, and you can trigger the Transformer anywhere using the Tab key. It's like having a smart machine that completes your thoughts 😀

Get started by typing a custom snippet, check out the repository, or try one of the examples. Have fun!