{"id":29157,"date":"2020-04-24T19:37:26","date_gmt":"2020-04-24T19:37:26","guid":{"rendered":"https:\/\/uscictdialdev.wpenginepowered.com\/?page_id=29157"},"modified":"2020-04-24T19:42:19","modified_gmt":"2020-04-24T19:42:19","slug":"huggingface","status":"publish","type":"page","link":"https:\/\/dialport.ict.usc.edu\/index.php\/huggingface\/","title":{"rendered":"Huggingface"},"content":{"rendered":"<p><a href=\"http:\/\/huggingface.co\">Home<\/a>\u00a0 \u00a0\u00a0<a href=\"https:\/\/huggingface.co\/transformers\/\">Transformers Docs<\/a>\u00a0 \u00a0\u00a0<a href=\"https:\/\/github.com\/huggingface\/transformers\">Github<\/a><\/p>\n<p>Huggingface is an API providing pre-trained transformers models implemented in PyTorch and Tensorflow, which are extremely useful for a variety of NLP tasks.<\/p>\n<p>Its Transformers library (formerly known as\u00a0<cite>pytorch-transformers<\/cite>\u00a0and\u00a0<cite>pytorch-pretrained-bert<\/cite>) provides general-purpose architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet\u2026) for Natural Language Understanding (NLU) and Natural Language Generation (NLG).<\/p>\n<p>Features:<\/p>\n<p>&#8211; High performance on NLU and NLG tasks<\/p>\n<p>&#8211; Low barrier to entry for educators and practitioners<\/p>\n<p>&#8211; State-of-the-art NLP for everyone<\/p>\n<ul>\n<li>Deep learning researchers<\/li>\n<li>Hands-on practitioners<\/li>\n<li>AI\/ML\/NLP teachers and educators<\/li>\n<\/ul>\n<p>&#8211; Lower compute costs, smaller carbon footprint<\/p>\n<ul>\n<li>Researchers can share trained models instead of always retraining<\/li>\n<li>Practitioners can reduce compute time and production costs<\/li>\n<li>Dozens of architectures with over 1,000 pretrained models, some in more than 100 languages<\/li>\n<\/ul>\n<p>&#8211; Choose the right framework for every part of a model&#8217;s lifetime<\/p>\n<ul>\n<li>Train state-of-the-art models in 3 lines of code<\/li>\n<li>Deep interoperability between TensorFlow 2.0 and PyTorch models<\/li>\n<li>Move a single model between TF2.0\/PyTorch frameworks at will<\/li>\n<li>Seamlessly pick the right framework for training, evaluation, production<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Home\u00a0 \u00a0\u00a0Transformers Docs\u00a0 \u00a0\u00a0Github Huggingface is an API providing pre-trained transformers models implemented in PyTorch and Tensorflow, which are extremely useful for a variety of NLP tasks. Its Transformers library (formerly known as\u00a0pytorch-transformers\u00a0and\u00a0pytorch-pretrained-bert) provides general-purpose architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet\u2026) for Natural Language Understanding (NLU) and Natural Language Generation (NLG). Features: &#8211; High [&hellip;]<\/p>\n","protected":false},"author":20,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-29157","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/pages\/29157","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/users\/20"}],"replies":[{"embeddable":true,"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/comments?post=29157"}],"version-history":[{"count":0,"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/pages\/29157\/revisions"}],"wp:attachment":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/media?parent=29157"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}