e:["$","main",null,{"className":"experience-detail page-container","children":[["$","$L10",null,{}],["$","section",null,{"className":"experience","children":[["$","$11",null,{"fallback":null,"children":["$","$L12",null,{}]}],["$","$11",null,{"fallback":null,"children":["$","$L13",null,{"experience":{"id":"cad9039c-6606-11ee-82a0-0242ac110002","type":"notebook","objectId":"nice-mink","background":"linear-gradient(180deg, #F472C0 0%, #5CA4ED 100%)","title":"transformer tutorial","userName":"riju+1220@deque.app","handle":"e05f7822-87e4-11ee-b05b-845cf32615c9","authors":[],"description":"$14","descriptionPlainText":"Language Modeling with nn.Transformer and torchtext\n\nThis is a tutorial on training a model to predict the next word in a sequence\nusing the nn.Transformer\n__ module.\n\nThe PyTorch 1.2 release includes a standard transformer module based on the\npaper Attention is All You Need . Compared\nto Recurrent Neural Networks (RNNs), the transformer model has proven to be\nsuperior in quality for many sequence-to-sequence tasks while being more\nparallelizable. The nn.Transformer module relies entirely on an attention\nmechanism (implemented as nn.MultiheadAttention\n) to\ndraw global dependencies between input and output. The nn.Transformer module is\nhighly modularized such that a single component (e.g., nn.TransformerEncoder\n__)\ncan be easily adapted/composed.","published":"Sun, 08 Oct 2023 18:16:25 GMT","tags":["transformers","pytorch"],"files":["users/riju+1220@deque.app/notebooks/nice-mink/transformer_tutorial.ipynb"],"mainFile":"users/riju+1220@deque.app/notebooks/nice-mink/transformer_tutorial.ipynb","sourceDir":"/","assets":[],"task":["Text Generation","Deep Learning Fundamentals"],"taskCategory":["Natural Language Processing","Deep Learning Fundamentals"]}}]}],["$","div",null,{"className":"experience-card","children":[["$","div",null,{"className":"cover","children":["$","div",null,{"className":"experience-tags","children":["$","div",null,{"className":"tags","children":[["$","div","transformers",{"className":"tag","children":"transformers"}],["$","div","pytorch",{"className":"tag","children":"pytorch"}]]}]}]}],["$","div",null,{"className":"description-and-actions","children":[["$","div",null,{"className":"col","children":["$","div",null,{"className":"description","children":"Language Modeling with nn.Transformer and torchtext\n\nThis is a tutorial on training a model to predict the next word in a sequence\nusing the nn.Transformer\n__ module.\n\nThe PyTorch 1.2 release includes a standard transformer module based on the\npaper Attention is All You Need . Compared\nto Recurrent Neural Networks (RNNs), the transformer model has proven to be\nsuperior in quality for many sequence-to-sequence tasks while being more\nparallelizable. The nn.Transformer module relies entirely on an attention\nmechanism (implemented as nn.MultiheadAttention\n) to\ndraw global dependencies between input and output. The nn.Transformer module is\nhighly modularized such that a single component (e.g., nn.TransformerEncoder\n__)\ncan be easily adapted/composed."}]}],["$","div",null,{"className":"col","children":["$","div",null,{"className":"actions","children":["$","$11",null,{"fallback":null,"children":["$","$L15",null,{"children":["$","$L16",null,{"experience":{"id":"cad9039c-6606-11ee-82a0-0242ac110002","type":"notebook","objectId":"nice-mink","background":"linear-gradient(180deg, #F472C0 0%, #5CA4ED 100%)","title":"transformer tutorial","userName":"riju+1220@deque.app","handle":"e05f7822-87e4-11ee-b05b-845cf32615c9","authors":[],"description":"$17","descriptionPlainText":"Language Modeling with nn.Transformer and torchtext\n\nThis is a tutorial on training a model to predict the next word in a sequence\nusing the nn.Transformer\n__ module.\n\nThe PyTorch 1.2 release includes a standard transformer module based on the\npaper Attention is All You Need . Compared\nto Recurrent Neural Networks (RNNs), the transformer model has proven to be\nsuperior in quality for many sequence-to-sequence tasks while being more\nparallelizable. The nn.Transformer module relies entirely on an attention\nmechanism (implemented as nn.MultiheadAttention\n) to\ndraw global dependencies between input and output. The nn.Transformer module is\nhighly modularized such that a single component (e.g., nn.TransformerEncoder\n__)\ncan be easily adapted/composed.","published":"Sun, 08 Oct 2023 18:16:25 GMT","tags":["transformers","pytorch"],"files":["users/riju+1220@deque.app/notebooks/nice-mink/transformer_tutorial.ipynb"],"mainFile":"users/riju+1220@deque.app/notebooks/nice-mink/transformer_tutorial.ipynb","sourceDir":"/","assets":[],"task":["Text Generation","Deep Learning Fundamentals"],"taskCategory":["Natural Language Processing","Deep Learning Fundamentals"]}}]}]}]}]}]]}]]}],["$","$L18",null,{"items":[{"label":"Summary","key":"summary","children":["$","div",null,{"className":"experience-data","children":[["$","div",null,{"className":"title","children":"transformer tutorial"}],["$","div",null,{"className":"markdown-description","children":[["$","h1","h1-0",{"children":["Language Modeling with ",["$","code","code-0",{"children":"nn.Transformer"}]," and torchtext"]}],"\n",["$","p","p-0",{"children":["This is a tutorial on training a model to predict the next word in a sequence using the\n",["$","code","code-0",{"children":"nn.Transformer "}],"__ module."]}],"\n",["$","p","p-1",{"children":["The PyTorch 1.2 release includes a standard transformer module based on the\npaper ",["$","code","code-0",{"children":"Attention is All You Need "}],["$","strong","strong-0",{"children":[".\nCompared to Recurrent Neural Networks (RNNs), the transformer model has proven\nto be superior in quality for many sequence-to-sequence tasks while being more\nparallelizable. The ",["$","code","code-0",{"children":"nn.Transformer"}]," module relies entirely on an attention\nmechanism (implemented as\n",["$","code","code-1",{"children":"nn.MultiheadAttention "}]]}],")\nto draw global dependencies between input and output. The ",["$","code","code-1",{"children":"nn.Transformer"}],"\nmodule is highly modularized such that a single component (e.g.,\n",["$","code","code-2",{"children":"nn.TransformerEncoder "}],"__)\ncan be easily adapted/composed."]}]]}],["$","br",null,{}],["$","div",null,{"className":"task","children":[["$","span",null,{"className":"task-label","children":"Tasks: "}],["$","span",null,{"className":"task","children":"Text Generation, Deep Learning Fundamentals"}]]}],["$","div",null,{"className":"task-category","children":[["$","span",null,{"className":"task-category-label","children":"Task Categories: "}],["$","span",null,{"className":"task-category","children":"Natural Language Processing, Deep Learning Fundamentals"}]]}]]}]},{"label":"Code","key":"code","children":["$","$L19",null,{"experience":{"id":"cad9039c-6606-11ee-82a0-0242ac110002","type":"notebook","objectId":"nice-mink","background":"linear-gradient(180deg, #F472C0 0%, #5CA4ED 100%)","title":"transformer tutorial","userName":"riju+1220@deque.app","handle":"e05f7822-87e4-11ee-b05b-845cf32615c9","authors":[],"description":"$1a","descriptionPlainText":"Language Modeling with nn.Transformer and torchtext\n\nThis is a tutorial on training a model to predict the next word in a sequence\nusing the nn.Transformer\n__ module.\n\nThe PyTorch 1.2 release includes a standard transformer module based on the\npaper Attention is All You Need . Compared\nto Recurrent Neural Networks (RNNs), the transformer model has proven to be\nsuperior in quality for many sequence-to-sequence tasks while being more\nparallelizable. The nn.Transformer module relies entirely on an attention\nmechanism (implemented as nn.MultiheadAttention\n) to\ndraw global dependencies between input and output. The nn.Transformer module is\nhighly modularized such that a single component (e.g., nn.TransformerEncoder\n__)\ncan be easily adapted/composed.","published":"Sun, 08 Oct 2023 18:16:25 GMT","tags":["transformers","pytorch"],"files":["users/riju+1220@deque.app/notebooks/nice-mink/transformer_tutorial.ipynb"],"mainFile":"users/riju+1220@deque.app/notebooks/nice-mink/transformer_tutorial.ipynb","sourceDir":"/","assets":[],"task":["Text Generation","Deep Learning Fundamentals"],"taskCategory":["Natural Language Processing","Deep Learning Fundamentals"]}}]}]}]]}],["$","$L1b",null,{}]]}]