Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
| <header> | |
| <img class="logo" src="/front/assets/unicorn-tweaked.svg"> | |
| <div class="title"> | |
| Write With Transformer | |
| </div> | |
| <div class="tagline"> | |
| Get a modern neural network to<br>auto-complete your thoughts. | |
| </div> | |
| </header> | |
| <div class="section-models"> | |
| <div class="container"> | |
| <div class="description"> | |
| This web app, built by the Hugging Face team, is the official demo of the | |
| <a href="https://github.com/huggingface/transformers"><code>🤗/transformers</code></a> | |
| repository's text generation capabilities. | |
| </div> | |
| <div class="github-repo"> | |
| <a | |
| class="github-button" | |
| href="https://github.com/huggingface/transformers" data-size="large" data-show-count="true" aria-label="Star huggingface/transformers on GitHub"> | |
| Star | |
| </a> | |
| </div> | |
| <div class="title-section">Models</div> | |
| <div class="model" data-tilt> | |
| <div class="model-title">🦄 GPT-2</div> | |
| <div class="model-details"> | |
| The almighty king of text generation, GPT-2 comes in four available sizes, only three of which have been publicly made available. Feared for its fake news generation capabilities, | |
| it currently stands as the most syntactically coherent model. A direct successor to the original GPT, it reinforces the already established pre-training/fine-tuning killer duo. | |
| From the paper: Language Models are Unsupervised Multitask Learners by Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei and Ilya Sutskever. | |
| </div> | |
| <div class="model-bottom"> | |
| <a class="btn btn-primary" href="/doc/gpt2-large">Start writing</a> | |
| </div> | |
| </div> | |
| <div class="model" data-tilt> | |
| <div class="model-title">💯 XLNet</div> | |
| <div class="model-details"> | |
| Overcoming the unidirectional limit while maintaining an independent masking algorithm based on permutation, XLNet improves upon the state-of-the-art autoregressive model that is TransformerXL. Using a bidirectional context while keeping its autoregressive approach, this model outperforms BERT on 20 tasks while keeping an impressive generative coherence. | |
| From the paper: XLNet: Generalized Autoregressive Pretraining for Language Understanding, by Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov and Quoc V. Le. | |
| </div> | |
| <div class="model-bottom"> | |
| <a class="btn btn-primary" href="/doc/xlnet">Start writing</a> | |
| </div> | |
| </div> | |
| <div class="model" data-tilt> | |
| <div class="model-title">☠️ GPT</div> | |
| <div class="model-details"> | |
| Released by OpenAI, this seminal architecture has shown that large gains on several NLP tasks can be achieved by generative pre-training a language model | |
| on unlabeled text before fine-tuning it on a downstream task. | |
| From the paper: Improving Language Understanding by Generative Pre-Training, by Alec Radford, Karthik Naraimhan, Tim Salimans and Ilya Sutskever. | |
| </div> | |
| <div class="model-bottom"> | |
| <a class="btn btn-primary" href="/doc/gpt">Start writing</a> | |
| </div> | |
| </div> | |
| <a href="/model/distil-gpt2"> | |
| <div class="model" data-tilt> | |
| <div class="model-title">🐎 DistilGPT-2</div> | |
| <div class="model-details"> | |
| The student of the now ubiquitous GPT-2 does not come short of its teacher’s expectations. | |
| Obtained by distillation, DistilGPT-2 weighs 37% less, and is twice as fast as its OpenAI counterpart, while keeping the same generative power. | |
| Runs smoothly on an iPhone 7. The dawn of lightweight generative <br>transformers? | |
| </div> | |
| <div class="model-bottom"> | |
| <a class="btn btn-details" href="/model/distil-gpt2">More info</a> | |
| <a class="btn btn-primary" href="/doc/distil-gpt2">Start writing</a> | |
| </div> | |
| </div> | |
| </a> | |
| <a href="/model/arxiv-nlp"> | |
| <div class="model" data-tilt> | |
| <div class="model-title">🤓 Arxiv-NLP</div> | |
| <div class="model-details"> | |
| Built on the OpenAI GPT-2 model, the Hugging Face team has fine-tuned the small version on a tiny dataset (60MB of text) of Arxiv papers. | |
| The targeted subject is Natural Language Processing, resulting in a very Linguistics/Deep Learning oriented generation. | |
| </div> | |
| <div class="model-bottom"> | |
| <a class="btn btn-details" href="/model/arxiv-nlp">More info</a> | |
| <a class="btn btn-primary" href="/doc/arxiv-nlp">Start writing</a> | |
| </div> | |
| </div> | |
| </a> | |
| <div class="description"> | |
| Do you want to contribute or suggest a new model checkpoint? Open an issue on | |
| <a href="https://github.com/huggingface/transformers"><code>🤗/transformers</code></a> 🔥. | |
| </div> | |
| <div class="quote"> | |
| “It is to writing what calculators are to calculus.” | |
| </div> | |
| </div> | |
| </div> | |
| <div class="section-footer"> | |
| <div class="container"> | |
| <div class="title"> | |
| Latest featured public documents | |
| </div> | |
| <ul class="documents"> | |
| {{#each docs}} | |
| <li> | |
| <a target="_blank" href="/share/{{this.shortId}}">{{ this.title }}</a> | |
| </li> | |
| {{else}} | |
| <li> | |
| <a target="_blank">None yet</a> | |
| </li> | |
| {{/each}} | |
| </ul> | |
| </div> | |
| </div> | |