Adding usage examples for common tasks (#2850)

* Usage: Sequence Classification & Question Answering * Pipeline example * Language modeling * TensorFlow code for Sequence classification * Custom TF/PT toggler in docs * QA + LM for TensorFlow * Finish Usage for both PyTorch and TensorFlow * Addressing Julien's comments * More assertive * cleanup * Favicon - added favicon option in conf.py along with the favicon image - udpated 🤗 logo. slightly smaller and should appear more consistent across editing programs (no more tongue on the outside of the mouth) Co-authored-by: joshchagani <joshua@joshuachagani.com>

Adding usage examples for common tasks (#2850)
* Usage: Sequence Classification & Question Answering * Pipeline example * Language modeling * TensorFlow code for Sequence classification * Custom TF/PT toggler in docs * QA + LM for TensorFlow * Finish Usage for both PyTorch and TensorFlow * Addressing Julien's comments * More assertive * cleanup * Favicon - added favicon option in conf.py along with the favicon image - udpated 🤗 logo. slightly smaller and should appear more consistent across editing programs (no more tongue on the outside of the mouth) Co-authored-by: joshchagani <joshua@joshuachagani.com>
65e7c90a · Lysandre Debut · GitHub · e693cd1e · 65e7c90a · 65e7c90a
Unverified Commit 65e7c90a authored Feb 25, 2020 by Lysandre Debut Committed by GitHub Feb 25, 2020
7 changed files
--- a/docs/source/_static/css/huggingface.css
+++ b/docs/source/_static/css/huggingface.css
+/* Our DOM objects */
+.framework-selector {
+    display: flex;
+    flex-direction: row;
+    justify-content: flex-end;
+}
+.framework-selector > button {
+    background-color: white;
+    color: #6670FF;
+    border: 1px solid #6670FF;
+    padding: 5px;
+}
+.framework-selector > button.selected{
+    background-color: #6670FF;
+    color: white;
+    border: 1px solid #6670FF;
+    padding: 5px;
+}
 /* The literal code blocks */
 .rst-content tt.literal, .rst-content tt.literal, .rst-content code.literal {
    color: #6670FF;

--- a/docs/source/_static/js/custom.js
+++ b/docs/source/_static/js/custom.js
@@ -68,6 +68,74 @@ function addHfMenu() {
    document.body.insertAdjacentHTML('afterbegin', div);
 }
+function platformToggle() {
+    const codeBlocks = Array.from(document.getElementsByClassName("highlight"));
+    const pytorchIdentifier = "## PYTORCH CODE";
+    const tensorflowIdentifier = "## TENSORFLOW CODE";
+    const pytorchSpanIdentifier = `<span class="c1">${pytorchIdentifier}</span>`;
+    const tensorflowSpanIdentifier = `<span class="c1">${tensorflowIdentifier}</span>`;
+    const getFrameworkSpans = filteredCodeBlock => {
+        const spans = filteredCodeBlock.element.innerHTML;
+        const pytorchSpanPosition = spans.indexOf(pytorchSpanIdentifier);
+        const tensorflowSpanPosition = spans.indexOf(tensorflowSpanIdentifier);
+        let pytorchSpans;
+        let tensorflowSpans;
+        if(pytorchSpanPosition < tensorflowSpanPosition){
+            pytorchSpans = spans.slice(pytorchSpanPosition + pytorchSpanIdentifier.length + 1, tensorflowSpanPosition);
+            tensorflowSpans = spans.slice(tensorflowSpanPosition + tensorflowSpanIdentifier.length + 1, spans.length);
+        }else{
+            tensorflowSpans = spans.slice(tensorflowSpanPosition + tensorflowSpanIdentifier.length + 1, pytorchSpanPosition);
+            pytorchSpans = spans.slice(pytorchSpanPosition + pytorchSpanIdentifier.length + 1, spans.length);
+        }
+        return {
+            ...filteredCodeBlock,
+            pytorchSample: pytorchSpans ,
+            tensorflowSample: tensorflowSpans
+        }
+    };
+    const createFrameworkButtons = sample => {
+            const pytorchButton = document.createElement("button");
+            pytorchButton.innerText = "PyTorch";
+            const tensorflowButton = document.createElement("button");
+            tensorflowButton.innerText = "TensorFlow";
+            const selectorDiv = document.createElement("div");
+            selectorDiv.classList.add("framework-selector");
+            selectorDiv.appendChild(pytorchButton);
+            selectorDiv.appendChild(tensorflowButton);
+            sample.element.parentElement.prepend(selectorDiv);
+            // Init on PyTorch
+            sample.element.innerHTML = sample.pytorchSample;
+            pytorchButton.classList.add("selected");
+            tensorflowButton.classList.remove("selected");
+            pytorchButton.addEventListener("click", () => {
+                sample.element.innerHTML = sample.pytorchSample;
+                pytorchButton.classList.add("selected");
+                tensorflowButton.classList.remove("selected");
+            });
+            tensorflowButton.addEventListener("click", () => {
+               sample.element.innerHTML = sample.tensorflowSample;
+                tensorflowButton.classList.add("selected");
+                pytorchButton.classList.remove("selected");
+            });
+        };
+    codeBlocks
+        .map(element => {return {element: element.firstChild, innerText: element.innerText}})
+        .filter(codeBlock => codeBlock.innerText.includes(pytorchIdentifier) && codeBlock.innerText.includes(tensorflowIdentifier))
+        .map(getFrameworkSpans)
+        .forEach(createFrameworkButtons);
+}
 /*!
 * github-buttons v2.2.10
 * (c) 2019 なつき
@@ -85,6 +153,7 @@ function onLoad() {
    addGithubButton();
    parseGithubButtons();
    addHfMenu();
+    platformToggle();
 }
 window.addEventListener("load", onLoad);
--- a/docs/source/_static/js/huggingface_logo.svg
+++ b/docs/source/_static/js/huggingface_logo.svg
-<svg width="95px" height="88px" viewBox="0 0 95 88" version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<svg clip-rule="evenodd" fill-rule="evenodd" stroke-linejoin="round" stroke-miterlimit="2" viewBox="0 0 127 118" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><clipPath id="a"><path clip-rule="nonzero" d="m62 75.052c13.105 0 17.333-11.684 17.333-17.684 0-3.118-2.096-2.136-5.453-.474-3.103 1.536-7.282 3.653-11.88 3.653-9.573 0-17.333-9.179-17.333-3.179s4.228 17.684 17.333 17.684z"/></clipPath><path d="m125.057 93.44c1 2.88.76 5.947-.573 8.613-.96 1.947-2.333 3.454-4.013 4.8-2.027 1.6-4.547 2.96-7.587 4.267-3.627 1.547-8.053 3-10.08 3.533-5.187 1.347-10.173 2.2-15.227 2.24-7.226.067-13.453-1.64-17.88-6-2.293.28-4.613.44-6.946.44-2.214 0-4.4-.133-6.574-.4-4.44 4.334-10.64 6.027-17.84 5.96-5.053-.04-10.04-.893-15.24-2.24-2.013-.533-6.44-1.986-10.066-3.533-3.04-1.307-5.56-2.667-7.574-4.267-1.693-1.346-3.066-2.853-4.026-4.8-1.32-2.666-1.574-5.733-.56-8.613-.934-2.2-1.174-4.72-.44-7.507.333-1.266.88-2.44 1.573-3.48-.147-.546-.267-1.106-.347-1.72-.506-3.653.76-6.986 3.147-9.573 1.173-1.293 2.44-2.187 3.76-2.76-.973-4.133-1.48-8.387-1.48-12.733 0-30.747 24.92-55.667 55.667-55.667 10.56 0 20.44 2.933 28.866 8.053 1.52.934 3.014 1.934 4.44 3 .707.534 1.414 1.08 2.094 1.654.693.56 1.373 1.146 2.026 1.746 1.974 1.8 3.827 3.734 5.52 5.8.574.68 1.12 1.387 1.654 2.107 1.08 1.427 2.08 2.907 3 4.44 1.4 2.293 2.626 4.693 3.693 7.187.707 1.666 1.32 3.373 1.867 5.12.813 2.613 1.44 5.306 1.866 8.08.134.92.254 1.853.347 2.786.187 1.867.293 3.76.293 5.694 0 4.293-.506 8.506-1.453 12.573 1.467.573 2.853 1.507 4.147 2.92 2.386 2.587 3.653 5.933 3.146 9.587-.08.6-.2 1.16-.346 1.706.693 1.04 1.24 2.214 1.573 3.48.733 2.787.493 5.307-.427 7.507" fill="#fff" fill-rule="nonzero"/><circle cx="62.333" cy="55.667" fill="#ffd21e" r="46.333"/><g fill-rule="nonzero"><path d="m108.667 55.667c0-25.59-20.744-46.334-46.334-46.334-25.589 0-46.333 20.744-46.333 46.334 0 25.589 20.744 46.333 46.333 46.333 25.59 0 46.334-20.744 46.334-46.333zm-98 0c0-28.535 23.132-51.667 51.666-51.667 28.535 0 51.667 23.132 51.667 51.667 0 28.534-23.132 51.666-51.667 51.666-28.534 0-51.666-23.132-51.666-51.666z" fill="#ffac03"/><path d="m77.387 43.055c1.7.6 2.376 4.093 4.092 3.181 3.251-1.729 4.485-5.765 2.757-9.016-1.729-3.251-5.765-4.485-9.016-2.757-3.251 1.729-4.485 5.765-2.757 9.016.816 1.535 3.406-.96 4.924-.424z" fill="#3a3b45"/><path d="m45.978 43.055c-1.699.6-2.375 4.093-4.092 3.181-3.251-1.729-4.485-5.765-2.756-9.016 1.728-3.251 5.765-4.485 9.016-2.757 3.251 1.729 4.485 5.765 2.756 9.016-.815 1.535-3.405-.96-4.924-.424z" fill="#3a3b45"/><path d="m62 75.052c13.105 0 17.333-11.684 17.333-17.684 0-3.118-2.096-2.136-5.453-.474-3.103 1.536-7.282 3.653-11.88 3.653-9.573 0-17.333-9.179-17.333-3.179s4.228 17.684 17.333 17.684z" fill="#3a3b45"/></g><g clip-path="url(#a)"><path d="m62.333 88.667c6.387 0 11.564-5.178 11.564-11.564 0-4.975-3.141-9.216-7.548-10.848-.162-.06-.326-.116-.491-.169-1.111-.355-2.296 3.464-3.525 3.464-1.148 0-2.257-3.844-3.305-3.532-4.776 1.422-8.259 5.847-8.259 11.085 0 6.386 5.178 11.564 11.564 11.564z" fill="#ef4e4e" fill-rule="nonzero"/></g><circle cx="93.667" cy="45" fill="#ffd21e" r="4.333"/><circle cx="31.667" cy="45" fill="#ffd21e" r="4.333"/><path d="m22.749 64c-2.158 0-4.088.887-5.433 2.495-.832.996-1.701 2.601-1.772 5.005-.905-.26-1.776-.405-2.589-.405-2.067 0-3.934.792-5.254 2.23-1.696 1.847-2.449 4.116-2.121 6.387.156 1.081.517 2.051 1.057 2.948-1.138.921-1.977 2.204-2.382 3.747-.318 1.209-.643 3.728 1.056 6.322-.108.17-.21.346-.304.526-1.022 1.938-1.087 4.129-.186 6.169 1.367 3.092 4.763 5.528 11.358 8.143 4.102 1.626 7.856 2.666 7.889 2.676 5.424 1.406 10.329 2.121 14.576 2.121 7.805 0 13.393-2.391 16.609-7.105 5.176-7.592 4.436-14.536-2.261-21.23-3.707-3.704-6.171-9.165-6.684-10.364-1.035-3.549-3.771-7.494-8.319-7.494h-.001c-.383 0-.769.03-1.151.09-1.992.314-3.733 1.46-4.977 3.186-1.343-1.67-2.647-2.998-3.827-3.747-1.778-1.128-3.556-1.7-5.284-1.7m0 5.333c.68 0 1.511.29 2.427.871 2.844 1.804 8.332 11.237 10.341 14.907.674 1.229 1.824 1.749 2.86 1.749 2.056 0 3.662-2.044.188-4.641-5.222-3.908-3.39-10.296-.897-10.69.109-.017.217-.025.321-.025 2.267 0 3.267 3.907 3.267 3.907s2.931 7.36 7.965 12.39c5.035 5.032 5.295 9.071 1.626 14.452-2.503 3.67-7.294 4.778-12.203 4.778-5.092 0-10.312-1.192-13.237-1.951-.144-.037-17.935-5.063-15.682-9.34.379-.719 1.003-1.007 1.788-1.007 3.174 0 8.946 4.723 11.427 4.723.555 0 .945-.236 1.105-.812 1.058-3.793-16.076-5.388-14.632-10.883.255-.972.946-1.366 1.916-1.365 4.194 0 13.602 7.375 15.574 7.375.15 0 .258-.044.317-.138.988-1.594.447-2.708-6.517-6.922-6.964-4.216-11.852-6.752-9.072-9.779.32-.349.773-.504 1.324-.504 4.228.001 14.217 9.092 14.217 9.092s2.696 2.804 4.327 2.804c.374 0 .693-.148.909-.513 1.156-1.95-10.737-10.963-11.408-14.682-.455-2.52.319-3.796 1.749-3.796" fill="#ffac03" fill-rule="nonzero"/><path d="m50.846 102.253c3.67-5.381 3.41-9.42-1.625-14.452-5.035-5.03-7.965-12.39-7.965-12.39s-1.095-4.275-3.588-3.882c-2.494.394-4.324 6.782.898 10.69 5.223 3.906-1.04 6.561-3.049 2.892-2.009-3.67-7.496-13.103-10.341-14.907-2.844-1.804-4.847-.793-4.176 2.925.67 3.719 12.565 12.732 11.408 14.683-1.158 1.949-5.236-2.292-5.236-2.292s-12.763-11.615-15.542-8.588c-2.778 3.027 2.108 5.563 9.072 9.779 6.966 4.214 7.506 5.328 6.518 6.922-.99 1.595-16.363-11.366-17.807-5.872-1.443 5.495 15.689 7.09 14.632 10.883-1.057 3.795-12.068-7.18-14.32-2.904-2.253 4.277 15.537 9.303 15.681 9.34 5.747 1.491 20.342 4.649 25.44-2.827" fill="#ffd21e" fill-rule="nonzero"/><path d="m102.584 64c2.159 0 4.088.887 5.433 2.495.832.996 1.702 2.601 1.772 5.005.906-.26 1.776-.405 2.59-.405 2.066 0 3.933.792 5.253 2.23 1.696 1.847 2.449 4.116 2.121 6.387-.156 1.081-.517 2.051-1.057 2.948 1.139.921 1.977 2.204 2.383 3.747.317 1.209.642 3.728-1.056 6.322.108.17.209.346.304.526 1.021 1.938 1.086 4.129.185 6.169-1.367 3.092-4.763 5.528-11.357 8.143-4.103 1.626-7.856 2.666-7.89 2.676-5.424 1.406-10.329 2.121-14.576 2.121-7.805 0-13.393-2.391-16.609-7.105-5.176-7.592-4.436-14.536 2.261-21.23 3.707-3.704 6.171-9.165 6.684-10.364 1.035-3.549 3.771-7.494 8.319-7.494h.001c.383 0 .77.03 1.151.09 1.992.314 3.733 1.46 4.977 3.186 1.343-1.67 2.647-2.998 3.827-3.747 1.779-1.128 3.556-1.7 5.284-1.7m0 5.333c-.68 0-1.511.29-2.427.871-2.844 1.804-8.332 11.237-10.341 14.907-.673 1.229-1.824 1.749-2.86 1.749-2.056 0-3.661-2.044-.188-4.641 5.223-3.908 3.391-10.296.897-10.69-.109-.017-.217-.025-.321-.025-2.267 0-3.267 3.907-3.267 3.907s-2.93 7.36-7.965 12.39c-5.035 5.032-5.295 9.071-1.625 14.452 2.502 3.67 7.293 4.778 12.202 4.778 5.092 0 10.312-1.192 13.238-1.951.144-.037 17.934-5.063 15.681-9.34-.379-.719-1.003-1.007-1.788-1.007-3.173 0-8.945 4.723-11.427 4.723-.554 0-.945-.236-1.105-.812-1.057-3.793 16.076-5.388 14.632-10.883-.255-.972-.945-1.366-1.916-1.365-4.193 0-13.601 7.375-15.573 7.375-.151 0-.259-.044-.318-.138-.988-1.594-.446-2.708 6.518-6.922 6.964-4.216 11.852-6.752 9.072-9.779-.32-.349-.774-.504-1.324-.504-4.228.001-14.218 9.092-14.218 9.092s-2.696 2.804-4.326 2.804c-.375 0-.694-.148-.91-.513-1.156-1.95 10.738-10.963 11.408-14.682.455-2.52-.318-3.796-1.749-3.796" fill="#ffac03" fill-rule="nonzero"/><path d="m74.487 102.253c-3.669-5.381-3.409-9.42 1.625-14.452 5.035-5.03 7.966-12.39 7.966-12.39s1.094-4.275 3.588-3.882c2.493.394 4.324 6.782-.899 10.69-5.223 3.906 1.04 6.561 3.049 2.892 2.01-3.67 7.496-13.103 10.342-14.907 2.844-1.804 4.846-.793 4.176 2.925-.671 3.719-12.566 12.732-11.408 14.683 1.157 1.949 5.236-2.292 5.236-2.292s12.762-11.615 15.541-8.588-2.108 5.563-9.072 9.779c-6.965 4.214-7.505 5.328-6.517 6.922.989 1.595 16.362-11.366 17.806-5.872 1.443 5.495-15.689 7.09-14.632 10.883 1.058 3.795 12.068-7.18 14.32-2.904 2.254 4.277-15.537 9.303-15.681 9.34-5.747 1.491-20.341 4.649-25.44-2.827" fill="#ffd21e" fill-rule="nonzero"/></svg>
-    <!-- Generator: Sketch 43.2 (39069) - http://www.bohemiancoding.com/sketch -->
\ No newline at end of file
-    <title>icon</title>
-    <desc>Created with Sketch.</desc>
-    <defs>
-        <path d="M13,14.7890193 C22.8284801,14.7890193 26,6.02605902 26,1.5261751 C26,-0.812484109 24.4279133,-0.0763570998 21.9099482,1.17020987 C19.5830216,2.32219957 16.4482998,3.91011313 13,3.91011313 C5.82029825,3.91011313 0,-2.97370882 0,1.5261751 C0,6.02605902 3.17151989,14.7890193 13,14.7890193 Z" id="path-1"></path>
-    </defs>
-    <g id="Page-1" stroke="none" stroke-width="1" fill="none" fill-rule="evenodd">
-        <g id="icon_desktop">
-            <g id="icon">
-                <g id="icon_desktop">
-                    <g id="Group-2">
-                        <g id="Group">
-                            <path d="M93.7930402,70.08 C94.5430402,72.24 94.3630402,74.54 93.3630402,76.54 C92.6430402,78 91.6130402,79.13 90.3530402,80.14 C88.8330402,81.34 86.9430402,82.36 84.6630402,83.34 C81.9430402,84.5 78.6230402,85.59 77.1030402,85.99 C73.2130402,87 69.4730402,87.64 65.6830402,87.67 C60.2630402,87.72 55.5930402,86.44 52.2730402,83.17 C50.5530402,83.38 48.8130402,83.5 47.0630402,83.5 C45.4030402,83.5 43.7630402,83.4 42.1330402,83.2 C38.8030402,86.45 34.1530402,87.72 28.7530402,87.67 C24.9630402,87.64 21.2230402,87 17.3230402,85.99 C15.8130402,85.59 12.4930402,84.5 9.77304019,83.34 C7.49304019,82.36 5.60304019,81.34 4.09304019,80.14 C2.82304019,79.13 1.79304019,78 1.07304019,76.54 C0.0830401858,74.54 -0.106959814,72.24 0.653040186,70.08 C-0.0469598142,68.43 -0.226959814,66.54 0.323040186,64.45 C0.573040186,63.5 0.983040186,62.62 1.50304019,61.84 C1.39304019,61.43 1.30304019,61.01 1.24304019,60.55 C0.863040186,57.81 1.81304019,55.31 3.60304019,53.37 C4.48304019,52.4 5.43304019,51.73 6.42304019,51.3 C5.69304019,48.2 5.31304019,45.01 5.31304019,41.75 C5.31304019,18.69 24.0030402,0 47.0630402,0 C54.9830402,0 62.3930402,2.2 68.7130402,6.04 C69.8530402,6.74 70.9730402,7.49 72.0430402,8.29 C72.5730402,8.69 73.1030402,9.1 73.6130402,9.53 C74.1330402,9.95 74.6430402,10.39 75.1330402,10.84 C76.6130402,12.19 78.0030402,13.64 79.2730402,15.19 C79.7030402,15.7 80.1130402,16.23 80.5130402,16.77 C81.3230402,17.84 82.0730402,18.95 82.7630402,20.1 C83.8130402,21.82 84.7330402,23.62 85.5330402,25.49 C86.0630402,26.74 86.5230402,28.02 86.9330402,29.33 C87.5430402,31.29 88.0130402,33.31 88.3330402,35.39 C88.4330402,36.08 88.5230402,36.78 88.5930402,37.48 C88.7330402,38.88 88.8130402,40.3 88.8130402,41.75 C88.8130402,44.97 88.4330402,48.13 87.7230402,51.18 C88.8230402,51.61 89.8630402,52.31 90.8330402,53.37 C92.6230402,55.31 93.5730402,57.82 93.1930402,60.56 C93.1330402,61.01 93.0430402,61.43 92.9330402,61.84 C93.4530402,62.62 93.8630402,63.5 94.1130402,64.45 C94.6630402,66.54 94.4830402,68.43 93.7930402,70.08" id="Fill-1" fill="#FFFFFF" fill-rule="nonzero"></path>
-                            <circle id="Oval" fill="#FFD21E" fill-rule="nonzero" cx="46.75" cy="41.75" r="34.75"></circle>
-                            <path d="M81.5,41.75 C81.5,22.5581049 65.9418951,7 46.75,7 C27.5581049,7 12,22.5581049 12,41.75 C12,60.9418951 27.5581049,76.5 46.75,76.5 C65.9418951,76.5 81.5,60.9418951 81.5,41.75 Z M8,41.75 C8,20.3489659 25.3489659,3 46.75,3 C68.1510341,3 85.5,20.3489659 85.5,41.75 C85.5,63.1510341 68.1510341,80.5 46.75,80.5 C25.3489659,80.5 8,63.1510341 8,41.75 Z" id="Oval" fill="#FFAC03" fill-rule="nonzero"></path>
-                            <path d="M57.1723547,31.7151181 C58.0863134,32.7107502 57.3040427,35.2620959 58.7620957,35.2620959 C61.5235194,35.2620959 63.7620957,33.0235196 63.7620957,30.2620959 C63.7620957,27.5006721 61.5235194,25.2620959 58.7620957,25.2620959 C56.0006719,25.2620959 53.7620957,27.5006721 53.7620957,30.2620959 C53.7620957,31.5654666 56.3553563,30.8251108 57.1723547,31.7151181 Z" id="Oval-2" fill="#3A3B45" fill-rule="nonzero" transform="translate(58.762096, 30.262096) rotate(-28.000000) translate(-58.762096, -30.262096) "></path>
-                            <path d="M32.1723553,31.7151181 C33.086314,32.7107502 32.3040433,35.2620959 33.7620963,35.2620959 C36.52352,35.2620959 38.7620963,33.0235196 38.7620963,30.2620959 C38.7620963,27.5006721 36.52352,25.2620959 33.7620963,25.2620959 C31.0006725,25.2620959 28.7620963,27.5006721 28.7620963,30.2620959 C28.7620963,31.5654666 31.3553569,30.8251108 32.1723553,31.7151181 Z" id="Oval-2" fill="#3A3B45" fill-rule="nonzero" transform="translate(33.762096, 30.262096) scale(-1, 1) rotate(-28.000000) translate(-33.762096, -30.262096) "></path>
-                            <g id="Oval-4" transform="translate(33.500000, 41.500000)">
-                                <g id="Mask" fill-rule="nonzero" fill="#3A3B45">
-                                    <path d="M13,14.7890193 C22.8284801,14.7890193 26,6.02605902 26,1.5261751 C26,-0.812484109 24.4279133,-0.0763570998 21.9099482,1.17020987 C19.5830216,2.32219957 16.4482998,3.91011313 13,3.91011313 C5.82029825,3.91011313 0,-2.97370882 0,1.5261751 C0,6.02605902 3.17151989,14.7890193 13,14.7890193 Z" id="path-1"></path>
-                                </g>
-                                <g id="Clipped">
-                                    <mask id="mask-2" fill="white">
-                                        <use xlink:href="#path-1"></use>
-                                    </mask>
-                                    <g id="path-1"></g>
-                                    <path d="M13.25,25 C18.0399291,25 21.9229338,21.1169953 21.9229338,16.3270662 C21.9229338,12.5962324 19.5672252,9.41560375 16.2620987,8.19147116 C16.1404592,8.14641904 16.0175337,8.10401696 15.8933923,8.06433503 C15.0599892,7.79793679 14.1717882,10.6623144 13.25,10.6623144 C12.3886883,10.6623144 11.5567012,7.77968641 10.7713426,8.01349068 C7.18916268,9.07991937 4.57706621,12.3984489 4.57706621,16.3270662 C4.57706621,21.1169953 8.46007093,25 13.25,25 Z" id="Shape" fill="#EF4E4E" fill-rule="nonzero" mask="url(#mask-2)"></path>
-                                </g>
-                            </g>
-                            <circle id="Oval-3" fill="#FFD21E" fill-rule="nonzero" style="mix-blend-mode: multiply;" cx="70.25" cy="33.75" r="3.25"></circle>
-                            <circle id="Oval-3" fill="#FFD21E" fill-rule="nonzero" style="mix-blend-mode: multiply;" cx="23.75" cy="33.75" r="3.25"></circle>
-                        </g>
-                    </g>
-                </g>
-                <g id="Group-4" transform="translate(3.000000, 48.000000)" fill-rule="nonzero">
-                    <path d="M14.0619453,0 L14.0619453,0 C12.4429453,0 10.9959453,0.665 9.98694534,1.871 C9.36294534,2.618 8.71094534,3.822 8.65794534,5.625 C7.97894534,5.43 7.32594534,5.321 6.71594534,5.321 C5.16594534,5.321 3.76594534,5.915 2.77594534,6.994 C1.50394534,8.379 0.938945345,10.081 1.18494534,11.784 C1.30194534,12.595 1.57294534,13.322 1.97794534,13.995 C1.12394534,14.686 0.494945345,15.648 0.190945345,16.805 C-0.0470546551,17.712 -0.291054655,19.601 0.982945345,21.547 C0.901945345,21.674 0.825945345,21.806 0.754945345,21.941 C-0.0110546551,23.395 -0.0600546551,25.038 0.615945345,26.568 C1.64094534,28.887 4.18794534,30.714 9.13394534,32.675 C12.2109453,33.895 15.0259453,34.675 15.0509453,34.682 C19.1189453,35.737 22.7979453,36.273 25.9829453,36.273 C31.8369453,36.273 36.0279453,34.48 38.4399453,30.944 C42.3219453,25.25 41.7669453,20.042 36.7439453,15.022 C33.9639453,12.244 32.1159453,8.148 31.7309453,7.249 C30.9549453,4.587 28.9029453,1.628 25.4919453,1.628 L25.4909453,1.628 C25.2039453,1.628 24.9139453,1.651 24.6279453,1.696 C23.1339453,1.931 21.8279453,2.791 20.8949453,4.085 C19.8879453,2.833 18.9099453,1.837 18.0249453,1.275 C16.6909453,0.429 15.3579453,0 14.0619453,0 M14.0619453,4 C14.5719453,4 15.1949453,4.217 15.8819453,4.653 C18.0149453,6.006 22.1309453,13.081 23.6379453,15.833 C24.1429453,16.755 25.0059453,17.145 25.7829453,17.145 C27.3249453,17.145 28.5289453,15.612 25.9239453,13.664 C22.0069453,10.733 23.3809453,5.942 25.2509453,5.647 C25.3329453,5.634 25.4139453,5.628 25.4919453,5.628 C27.1919453,5.628 27.9419453,8.558 27.9419453,8.558 C27.9419453,8.558 30.1399453,14.078 33.9159453,17.851 C37.6919453,21.625 37.8869453,24.654 35.1349453,28.69 C33.2579453,31.442 29.6649453,32.273 25.9829453,32.273 C22.1639453,32.273 18.2489453,31.379 16.0549453,30.81 C15.9469453,30.782 2.60394534,27.013 4.29394534,23.805 C4.57794534,23.266 5.04594534,23.05 5.63494534,23.05 C8.01494534,23.05 12.3439453,26.592 14.2049453,26.592 C14.6209453,26.592 14.9139453,26.415 15.0339453,25.983 C15.8269453,23.138 2.97694534,21.942 4.05994534,17.821 C4.25094534,17.092 4.76894534,16.796 5.49694534,16.797 C8.64194534,16.797 15.6979453,22.328 17.1769453,22.328 C17.2899453,22.328 17.3709453,22.295 17.4149453,22.225 C18.1559453,21.029 17.7499453,20.194 12.5269453,17.033 C7.30394534,13.871 3.63794534,11.969 5.72294534,9.699 C5.96294534,9.437 6.30294534,9.321 6.71594534,9.321 C9.88694534,9.322 17.3789453,16.14 17.3789453,16.14 C17.3789453,16.14 19.4009453,18.243 20.6239453,18.243 C20.9049453,18.243 21.1439453,18.132 21.3059453,17.858 C22.1729453,16.396 13.2529453,9.636 12.7499453,6.847 C12.4089453,4.957 12.9889453,4 14.0619453,4" id="Fill-1" fill="#FFAC03"></path>
-                    <path d="M35.1348,28.6899 C37.8868,24.6539 37.6918,21.6249 33.9158,17.8509 C30.1398,14.0779 27.9418,8.5579 27.9418,8.5579 C27.9418,8.5579 27.1208,5.3519 25.2508,5.6469 C23.3808,5.9419 22.0078,10.7329 25.9248,13.6639 C29.8418,16.5939 25.1448,18.5849 23.6378,15.8329 C22.1308,13.0809 18.0158,6.0059 15.8818,4.6529 C13.7488,3.2999 12.2468,4.0579 12.7498,6.8469 C13.2528,9.6359 22.1738,16.3959 21.3058,17.8589 C20.4378,19.3209 17.3788,16.1399 17.3788,16.1399 C17.3788,16.1399 7.8068,7.4289 5.7228,9.6989 C3.6388,11.9689 7.3038,13.8709 12.5268,17.0329 C17.7508,20.1939 18.1558,21.0289 17.4148,22.2249 C16.6728,23.4209 5.1428,13.6999 4.0598,17.8209 C2.9778,21.9419 15.8268,23.1379 15.0338,25.9829 C14.2408,28.8289 5.9828,20.5979 4.2938,23.8049 C2.6038,27.0129 15.9468,30.7819 16.0548,30.8099 C20.3648,31.9279 31.3108,34.2969 35.1348,28.6899" id="Fill-4" fill="#FFD21E"></path>
-                </g>
-                <g id="Group-4" transform="translate(70.500000, 66.500000) scale(-1, 1) translate(-70.500000, -66.500000) translate(50.000000, 48.000000)" fill-rule="nonzero">
-                    <path d="M14.0619453,0 L14.0619453,0 C12.4429453,0 10.9959453,0.665 9.98694534,1.871 C9.36294534,2.618 8.71094534,3.822 8.65794534,5.625 C7.97894534,5.43 7.32594534,5.321 6.71594534,5.321 C5.16594534,5.321 3.76594534,5.915 2.77594534,6.994 C1.50394534,8.379 0.938945345,10.081 1.18494534,11.784 C1.30194534,12.595 1.57294534,13.322 1.97794534,13.995 C1.12394534,14.686 0.494945345,15.648 0.190945345,16.805 C-0.0470546551,17.712 -0.291054655,19.601 0.982945345,21.547 C0.901945345,21.674 0.825945345,21.806 0.754945345,21.941 C-0.0110546551,23.395 -0.0600546551,25.038 0.615945345,26.568 C1.64094534,28.887 4.18794534,30.714 9.13394534,32.675 C12.2109453,33.895 15.0259453,34.675 15.0509453,34.682 C19.1189453,35.737 22.7979453,36.273 25.9829453,36.273 C31.8369453,36.273 36.0279453,34.48 38.4399453,30.944 C42.3219453,25.25 41.7669453,20.042 36.7439453,15.022 C33.9639453,12.244 32.1159453,8.148 31.7309453,7.249 C30.9549453,4.587 28.9029453,1.628 25.4919453,1.628 L25.4909453,1.628 C25.2039453,1.628 24.9139453,1.651 24.6279453,1.696 C23.1339453,1.931 21.8279453,2.791 20.8949453,4.085 C19.8879453,2.833 18.9099453,1.837 18.0249453,1.275 C16.6909453,0.429 15.3579453,0 14.0619453,0 M14.0619453,4 C14.5719453,4 15.1949453,4.217 15.8819453,4.653 C18.0149453,6.006 22.1309453,13.081 23.6379453,15.833 C24.1429453,16.755 25.0059453,17.145 25.7829453,17.145 C27.3249453,17.145 28.5289453,15.612 25.9239453,13.664 C22.0069453,10.733 23.3809453,5.942 25.2509453,5.647 C25.3329453,5.634 25.4139453,5.628 25.4919453,5.628 C27.1919453,5.628 27.9419453,8.558 27.9419453,8.558 C27.9419453,8.558 30.1399453,14.078 33.9159453,17.851 C37.6919453,21.625 37.8869453,24.654 35.1349453,28.69 C33.2579453,31.442 29.6649453,32.273 25.9829453,32.273 C22.1639453,32.273 18.2489453,31.379 16.0549453,30.81 C15.9469453,30.782 2.60394534,27.013 4.29394534,23.805 C4.57794534,23.266 5.04594534,23.05 5.63494534,23.05 C8.01494534,23.05 12.3439453,26.592 14.2049453,26.592 C14.6209453,26.592 14.9139453,26.415 15.0339453,25.983 C15.8269453,23.138 2.97694534,21.942 4.05994534,17.821 C4.25094534,17.092 4.76894534,16.796 5.49694534,16.797 C8.64194534,16.797 15.6979453,22.328 17.1769453,22.328 C17.2899453,22.328 17.3709453,22.295 17.4149453,22.225 C18.1559453,21.029 17.7499453,20.194 12.5269453,17.033 C7.30394534,13.871 3.63794534,11.969 5.72294534,9.699 C5.96294534,9.437 6.30294534,9.321 6.71594534,9.321 C9.88694534,9.322 17.3789453,16.14 17.3789453,16.14 C17.3789453,16.14 19.4009453,18.243 20.6239453,18.243 C20.9049453,18.243 21.1439453,18.132 21.3059453,17.858 C22.1729453,16.396 13.2529453,9.636 12.7499453,6.847 C12.4089453,4.957 12.9889453,4 14.0619453,4" id="Fill-1" fill="#FFAC03"></path>
-                    <path d="M35.1348,28.6899 C37.8868,24.6539 37.6918,21.6249 33.9158,17.8509 C30.1398,14.0779 27.9418,8.5579 27.9418,8.5579 C27.9418,8.5579 27.1208,5.3519 25.2508,5.6469 C23.3808,5.9419 22.0078,10.7329 25.9248,13.6639 C29.8418,16.5939 25.1448,18.5849 23.6378,15.8329 C22.1308,13.0809 18.0158,6.0059 15.8818,4.6529 C13.7488,3.2999 12.2468,4.0579 12.7498,6.8469 C13.2528,9.6359 22.1738,16.3959 21.3058,17.8589 C20.4378,19.3209 17.3788,16.1399 17.3788,16.1399 C17.3788,16.1399 7.8068,7.4289 5.7228,9.6989 C3.6388,11.9689 7.3038,13.8709 12.5268,17.0329 C17.7508,20.1939 18.1558,21.0289 17.4148,22.2249 C16.6728,23.4209 5.1428,13.6999 4.0598,17.8209 C2.9778,21.9419 15.8268,23.1379 15.0338,25.9829 C14.2408,28.8289 5.9828,20.5979 4.2938,23.8049 C2.6038,27.0129 15.9468,30.7819 16.0548,30.8099 C20.3648,31.9279 31.3108,34.2969 35.1348,28.6899" id="Fill-4" fill="#FFD21E"></path>
-                </g>
-            </g>
-        </g>
-    </g>
-</svg>
\ No newline at end of file
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -20,7 +20,7 @@ sys.path.insert(0, os.path.abspath('../../src'))
 # -- Project information -----------------------------------------------------
 project = u'transformers'
-copyright = u'2019, huggingface'
+copyright = u'2020, huggingface'
 author = u'huggingface'
 # The short X.Y version
@@ -105,6 +105,12 @@ html_static_path = ['_static']
 #
 # html_sidebars = {}
+# This must be the name of an image file (path relative to the configuration 
+# directory) that is the favicon of the docs. Modern browsers use this as 
+# the icon for tabs, windows and bookmarks. It should be a Windows-style 
+# icon file (.ico).
+html_favicon = 'favicon.ico'
 # -- Options for HTMLHelp output ---------------------------------------------

--- a/docs/source/favicon.ico
+++ b/docs/source/favicon.ico
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -61,6 +61,7 @@ The library currently contains PyTorch and Tensorflow implementations, pre-train
    quickstart
    glossary
    pretrained_models
+    usage
    model_sharing
    examples
    notebooks

--- a/docs/source/usage.rst
+++ b/docs/source/usage.rst
+Usage
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+This page shows the most frequent use-cases when using the library. The models available allow for many different
+configurations and a great versatility in use-cases. The most simple ones are presented here, showcasing usage
+for tasks such as question answering, sequence classification, named entity recognition and others.
+These examples leverage auto-models, which are classes that will instantiate a model according to a given checkpoint,
+automatically selecting the correct model architecture. Please check the :class:`~transformers.AutoModel` documentation
+for more information.
+Feel free to modify the code to be more specific and adapt it to your specific use-case.
+In order for a model to perform well on a task, it must be loaded from a checkpoint corresponding to that task. These
+checkpoints are usually pre-trained on a large corpus of data and fine-tuned on a specific task. This means the
+following:
+- Not all models were fine-tuned on all tasks. If you want to fine-tune a model on a specific task, you can leverage
+  one of the `run_$TASK.py` script in the
+  `examples <https://github.com/huggingface/transformers/tree/master/examples>`_ directory.
+- Fine-tuned models were fine-tuned on a specific dataset. This dataset may or may not overlap with your use-case
+  and domain. As mentioned previously, you may leverage the
+  `examples <https://github.com/huggingface/transformers/tree/master/examples>`_ scripts to fine-tune your model, or you
+  may create your own training script.
+In order to do an inference on a task, several mechanisms are made available by the library:
+- Pipelines: very easy-to-use abstractions, which require as little as two lines of code.
+- Using a model directly with a tokenizer (PyTorch/TensorFlow): the full inference using the model. Less abstraction,
+  but much more powerful.
+Both approaches are showcased here.
+.. note::
+    All tasks presented here leverage pre-trained checkpoints that were fine-tuned on specific tasks. Loading a
+    checkpoint that was not fine-tuned on a specific task would load only the base transformer layers and not the
+    additional head that is used for the task, initializing the weights of that head randomly.
+    This would produce random output.
+Sequence Classification
+--------------------------
+Sequence classification is the task of classifying sequences according to a given number of classes. An example
+of sequence classification is the GLUE dataset, which is entirely based on that task. If you would like to fine-tune
+a model on a GLUE sequence classification task, you may leverage the
+`run_glue.py <https://github.com/huggingface/transformers/tree/master/examples/run_glue.py>`_ or
+`run_tf_glue.py <https://github.com/huggingface/transformers/tree/master/examples/run_tf_glue.py>`_ scripts.
+Here is an example using the pipelines do to sentiment analysis: identifying if a sequence is positive or negative.
+It leverages a fine-tuned model on sst2, which is a GLUE task.
+::
+    from transformers import pipeline
+    nlp = pipeline("sentiment-analysis")
+    print(nlp("I hate you"))
+    print(nlp("I love you"))
+This returns a label ("POSITIVE" or "NEGATIVE") alongside a score, as follows:
+::
+    [{'label': 'NEGATIVE', 'score': 0.9991129}]
+    [{'label': 'POSITIVE', 'score': 0.99986565}]
+Here is an example of doing a sequence classification using a model to determine if two sequences are paraphrases
+of each other. The process is the following:
+- Instantiate a tokenizer and a model from the checkpoint name. The model is identified as a BERT model and loads it
+  with the weights stored in the checkpoint.
+- Build a sequence from the two sentences, with the correct model-specific separators token type ids
+  and attention masks (:func:`~transformers.PreTrainedTokenizer.encode` and
+  :func:`~transformers.PreTrainedTokenizer.encode_plus` take care of this)
+- Pass this sequence through the model so that it is classified in one of the two available classes: 0
+  (not a paraphrase) and 1 (is a paraphrase)
+- Compute the softmax of the result to get probabilities over the classes
+- Print the results
+::
+    ## PYTORCH CODE
+    from transformers import AutoTokenizer, AutoModelForSequenceClassification
+    import torch
+    tokenizer = AutoTokenizer.from_pretrained("bert-base-cased-finetuned-mrpc")
+    model = AutoModelForSequenceClassification.from_pretrained("bert-base-cased-finetuned-mrpc")
+    classes = ["not paraphrase", "is paraphrase"]
+    sequence_0 = "The company HuggingFace is based in New York City"
+    sequence_1 = "Apples are especially bad for your health"
+    sequence_2 = "HuggingFace's headquarters are situated in Manhattan"
+    paraphrase = tokenizer.encode_plus(sequence_0, sequence_2, return_tensors="pt")
+    not_paraphrase = tokenizer.encode_plus(sequence_0, sequence_1, return_tensors="pt")
+    paraphrase_classification_logits = model(**paraphrase)[0]
+    not_paraphrase_classification_logits = model(**not_paraphrase)[0]
+    paraphrase_results = torch.softmax(paraphrase_classification_logits, dim=1).tolist()[0]
+    not_paraphrase_results = torch.softmax(not_paraphrase_classification_logits, dim=1).tolist()[0]
+    print("Should be paraphrase")
+    for i in range(len(classes)):
+        print(f"{classes[i]}: {round(paraphrase_results[i] * 100)}%")
+    print("\nShould not be paraphrase")
+    for i in range(len(classes)):
+        print(f"{classes[i]}: {round(not_paraphrase_results[i] * 100)}%")
+    ## TENSORFLOW CODE
+    from transformers import AutoTokenizer, TFAutoModelForSequenceClassification
+    import tensorflow as tf
+    tokenizer = AutoTokenizer.from_pretrained("bert-base-cased-finetuned-mrpc")
+    model = TFAutoModelForSequenceClassification.from_pretrained("bert-base-cased-finetuned-mrpc")
+    classes = ["not paraphrase", "is paraphrase"]
+    sequence_0 = "The company HuggingFace is based in New York City"
+    sequence_1 = "Apples are especially bad for your health"
+    sequence_2 = "HuggingFace's headquarters are situated in Manhattan"
+    paraphrase = tokenizer.encode_plus(sequence_0, sequence_2, return_tensors="tf")
+    not_paraphrase = tokenizer.encode_plus(sequence_0, sequence_1, return_tensors="tf")
+    paraphrase_classification_logits = model(paraphrase)[0]
+    not_paraphrase_classification_logits = model(not_paraphrase)[0]
+    paraphrase_results = tf.nn.softmax(paraphrase_classification_logits, axis=1).numpy()[0]
+    not_paraphrase_results = tf.nn.softmax(not_paraphrase_classification_logits, axis=1).numpy()[0]
+    print("Should be paraphrase")
+    for i in range(len(classes)):
+        print(f"{classes[i]}: {round(paraphrase_results[i] * 100)}%")
+    print("\nShould not be paraphrase")
+    for i in range(len(classes)):
+        print(f"{classes[i]}: {round(not_paraphrase_results[i] * 100)}%")
+This outputs the following results:
+::
+    Should be paraphrase
+    not paraphrase: 10%
+    is paraphrase: 90%
+    Should not be paraphrase
+    not paraphrase: 94%
+    is paraphrase: 6%
+Extractive Question Answering
+----------------------------------------------------
+Extractive Question Answering is the task of extracting an answer from a text given a question. An example of a
+question answering dataset is the SQuAD dataset, which is entirely based on that task. If you would like to fine-tune
+a model on a SQuAD task, you may leverage the `run_squad.py`.
+Here is an example using the pipelines do to question answering: extracting an answer from a text given a question.
+It leverages a fine-tuned model on SQuAD.
+::
+    from transformers import pipeline
+    nlp = pipeline("question-answering")
+    context = r"""
+    Extractive Question Answering is the task of extracting an answer from a text given a question. An example of a
+    question answering dataset is the SQuAD dataset, which is entirely based on that task. If you would like to fine-tune
+    a model on a SQuAD task, you may leverage the `run_squad.py`.
+    """
+    print(nlp(question="What is extractive question answering?", context=context))
+    print(nlp(question="What is a good example of a question answering dataset?", context=context))
+This returns an answer extracted from the text, a confidence score, alongside "start" and "end" values which
+are the positions of the extracted answer in the text.
+::
+    {'score': 0.622232091629833, 'start': 34, 'end': 96, 'answer': 'the task of extracting an answer from a text given a question.'}
+    {'score': 0.5115299158662765, 'start': 147, 'end': 161, 'answer': 'SQuAD dataset,'}
+Here is an example of question answering using a model and a tokenizer. The process is the following:
+- Instantiate a tokenizer and a model from the checkpoint name. The model is identified as a BERT model and loads it
+  with the weights stored in the checkpoint.
+- Define a text and a few questions.
+- Iterate over the questions and build a sequence from the text and the current question, with the correct
+  model-specific separators token type ids and attention masks
+- Pass this sequence through the model. This outputs a range of scores across the entire sequence tokens (question and
+  text), for both the start and end positions.
+- Compute the softmax of the result to get probabilities over the tokens
+- Fetch the tokens from the identified start and stop values, convert those tokens to a string.
+- Print the results
+::
+    ## PYTORCH CODE
+    from transformers import AutoTokenizer, AutoModelForQuestionAnswering
+    import torch
+    tokenizer = AutoTokenizer.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
+    model = AutoModelForQuestionAnswering.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
+    text = r"""
+    🤗 Transformers (formerly known as pytorch-transformers and pytorch-pretrained-bert) provides general-purpose
+    architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet…) for Natural Language Understanding (NLU) and Natural
+    Language Generation (NLG) with over 32+ pretrained models in 100+ languages and deep interoperability between
+    TensorFlow 2.0 and PyTorch.
+    """
+    questions = [
+        "How many pretrained models are available in Transformers?",
+        "What does Transformers provide?",
+        "Transformers provides interoperability between which frameworks?",
+    ]
+    for question in questions:
+        inputs = tokenizer.encode_plus(question, text, add_special_tokens=True, return_tensors="pt")
+        input_ids = inputs["input_ids"].tolist()[0]
+        text_tokens = tokenizer.convert_ids_to_tokens(input_ids)
+        answer_start_scores, answer_end_scores = model(**inputs)
+        answer_start = torch.argmax(
+            answer_start_scores
+        )  # Get the most likely beginning of answer with the argmax of the score
+        answer_end = torch.argmax(answer_end_scores) + 1  # Get the most likely end of answer with the argmax of the score
+        answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end]))
+        print(f"Question: {question}")
+        print(f"Answer: {answer}\n")
+    ## TENSORFLOW CODE
+    from transformers import AutoTokenizer, TFAutoModelForQuestionAnswering
+    import tensorflow as tf
+    tokenizer = AutoTokenizer.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
+    model = TFAutoModelForQuestionAnswering.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
+    text = r"""
+    🤗 Transformers (formerly known as pytorch-transformers and pytorch-pretrained-bert) provides general-purpose
+    architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet…) for Natural Language Understanding (NLU) and Natural
+    Language Generation (NLG) with over 32+ pretrained models in 100+ languages and deep interoperability between
+    TensorFlow 2.0 and PyTorch.
+    """
+    questions = [
+        "How many pretrained models are available in Transformers?",
+        "What does Transformers provide?",
+        "Transformers provides interoperability between which frameworks?",
+    ]
+    for question in questions:
+        inputs = tokenizer.encode_plus(question, text, add_special_tokens=True, return_tensors="tf")
+        input_ids = inputs["input_ids"].numpy()[0]
+        text_tokens = tokenizer.convert_ids_to_tokens(input_ids)
+        answer_start_scores, answer_end_scores = model(inputs)
+        answer_start = tf.argmax(
+            answer_start_scores, axis=1
+        ).numpy()[0]  # Get the most likely beginning of answer with the argmax of the score
+        answer_end = (
+            tf.argmax(answer_end_scores, axis=1) + 1
+        ).numpy()[0]  # Get the most likely end of answer with the argmax of the score
+        answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end]))
+        print(f"Question: {question}")
+        print(f"Answer: {answer}\n")
+This outputs the questions followed by the predicted answers:
+::
+    Question: How many pretrained models are available in Transformers?
+    Answer: over 32 +
+    Question: What does Transformers provide?
+    Answer: general - purpose architectures
+    Question: Transformers provides interoperability between which frameworks?
+    Answer: tensorflow 2 . 0 and pytorch
+Language Modeling
+----------------------------------------------------
+Language modeling is the task of fitting a model to a corpus, which can be domain specific. All popular transformer
+based models are trained using a variant of language modeling, e.g. BERT with masked language modeling, GPT-2 with
+causal language modeling.
+Language modeling can be useful outside of pre-training as well, for example to shift the model distribution to be
+domain-specific: using a language model trained over a very large corpus, and then fine-tuning it to a news dataset
+or on scientific papers e.g. `LysandreJik/arxiv-nlp <https://huggingface.co/lysandre/arxiv-nlp>`__.
+Masked Language Modeling
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Masked language modeling is the task of masking tokens in a sequence with a masking token, and prompting the model to
+fill that mask with an appropriate token. This allows the model to attend to both the right context (tokens on the
+right of the mask) and the left context (tokens on the left of the mask). Such a training creates a strong basis
+for downstream tasks requiring bi-directional context such as SQuAD (question answering,
+see `Lewis, Lui, Goyal et al. <https://arxiv.org/abs/1910.13461>`__, part 4.2).
+Here is an example of using pipelines to replace a mask from a sequence:
+::
+    from transformers import pipeline
+    nlp = pipeline("fill-mask")
+    print(nlp(f"HuggingFace is creating a {nlp.tokenizer.mask_token} that the community uses to solve NLP tasks."))
+This outputs the sequences with the mask filled, the confidence score as well as the token id in the tokenizer
+vocabulary:
+::
+    [
+        {'sequence': '<s> HuggingFace is creating a tool that the community uses to solve NLP tasks.</s>', 'score': 0.15627853572368622, 'token': 3944},
+        {'sequence': '<s> HuggingFace is creating a framework that the community uses to solve NLP tasks.</s>', 'score': 0.11690319329500198, 'token': 7208},
+        {'sequence': '<s> HuggingFace is creating a library that the community uses to solve NLP tasks.</s>', 'score': 0.058063216507434845, 'token': 5560},
+        {'sequence': '<s> HuggingFace is creating a database that the community uses to solve NLP tasks.</s>', 'score': 0.04211743175983429, 'token': 8503},
+        {'sequence': '<s> HuggingFace is creating a prototype that the community uses to solve NLP tasks.</s>', 'score': 0.024718601256608963, 'token': 17715}
+    ]
+Here is an example doing masked language modeling using a model and a tokenizer. The process is the following:
+- Instantiate a tokenizer and a model from the checkpoint name. The model is identified as a DistilBERT model and
+  loads it with the weights stored in the checkpoint.
+- Define a sequence with a masked token, placing the :obj:`tokenizer.mask_token` instead of a word.
+- Encode that sequence into IDs and find the position of the masked token in that list of IDs.
+- Retrieve the predictions at the index of the mask token: this tensor has the same size as the vocabulary, and the
+  values are the scores attributed to each token. The model gives higher score to tokens he deems probable in that
+  context.
+- Retrieve the top 5 tokens using the PyTorch :obj:`topk` or TensorFlow :obj:`top_k` methods.
+- Replace the mask token by the tokens and print the results
+::
+    ## PYTORCH CODE
+    from transformers import AutoModelWithLMHead, AutoTokenizer
+    import torch
+    tokenizer = AutoTokenizer.from_pretrained("distilbert-base-cased")
+    model = AutoModelWithLMHead.from_pretrained("distilbert-base-cased")
+    sequence = f"Distilled models are smaller than the models they mimic. Using them instead of the large versions would help {tokenizer.mask_token} our carbon footprint."
+    input = tokenizer.encode(sequence, return_tensors="pt")
+    mask_token_index = torch.where(input == tokenizer.mask_token_id)[1]
+    token_logits = model(input)[0]
+    mask_token_logits = token_logits[0, mask_token_index, :]
+    top_5_tokens = torch.topk(mask_token_logits, 5, dim=1).indices[0].tolist()
+    for token in top_5_tokens:
+        print(sequence.replace(tokenizer.mask_token, tokenizer.decode([token])))
+    ## TENSORFLOW CODE
+    from transformers import TFAutoModelWithLMHead, AutoTokenizer
+    import tensorflow as tf
+    tokenizer = AutoTokenizer.from_pretrained("distilbert-base-cased")
+    model = TFAutoModelWithLMHead.from_pretrained("distilbert-base-cased")
+    sequence = f"Distilled models are smaller than the models they mimic. Using them instead of the large versions would help {tokenizer.mask_token} our carbon footprint."
+    input = tokenizer.encode(sequence, return_tensors="tf")
+    mask_token_index = tf.where(input == tokenizer.mask_token_id)[0, 1]
+    token_logits = model(input)[0]
+    mask_token_logits = token_logits[0, mask_token_index, :]
+    top_5_tokens = tf.math.top_k(mask_token_logits, 5).indices.numpy()
+    for token in top_5_tokens:
+        print(sequence.replace(tokenizer.mask_token, tokenizer.decode([token])))
+This prints five sequences, with the top 5 tokens predicted by the model:
+::
+    Distilled models are smaller than the models they mimic. Using them instead of the large versions would help reduce our carbon footprint.
+    Distilled models are smaller than the models they mimic. Using them instead of the large versions would help increase our carbon footprint.
+    Distilled models are smaller than the models they mimic. Using them instead of the large versions would help decrease our carbon footprint.
+    Distilled models are smaller than the models they mimic. Using them instead of the large versions would help offset our carbon footprint.
+    Distilled models are smaller than the models they mimic. Using them instead of the large versions would help improve our carbon footprint.
+Causal Language Modeling
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Causal language modeling is the task of predicting the token following a sequence of tokens. In this situation, the
+model only attends to the left context (tokens on the left of the mask). Such a training is particularly interesting
+for generation tasks.
+There is currently no pipeline to do causal language modeling/generation.
+Here is an example using the tokenizer and model. leveraging the :func:`~transformers.PreTrainedModel.generate` method
+to generate the tokens following the initial sequence in PyTorch, and creating a simple loop in TensorFlow.
+::
+    ## PYTORCH CODE
+    from transformers import AutoModelWithLMHead, AutoTokenizer
+    tokenizer = AutoTokenizer.from_pretrained("gpt2")
+    model = AutoModelWithLMHead.from_pretrained("gpt2")
+    sequence = f"Hugging Face is based in DUMBO, New York City, and is"
+    input = tokenizer.encode(sequence, return_tensors="pt")
+    generated = model.generate(input, max_length=50)
+    resulting_string = tokenizer.decode(generated.tolist()[0])
+    print(resulting_string)
+    ## TENSORFLOW CODE
+    from transformers import TFAutoModelWithLMHead, AutoTokenizer
+    import tensorflow as tf
+    tokenizer = AutoTokenizer.from_pretrained("gpt2")
+    model = TFAutoModelWithLMHead.from_pretrained("gpt2")
+    sequence = f"Hugging Face is based in DUMBO, New York City, and is"
+    generated = tokenizer.encode(sequence)
+    for i in range(50):
+        predictions = model(tf.constant([generated]))[0]
+        token = tf.argmax(predictions[0], axis=1)[-1].numpy()
+        generated += [token]
+    resulting_string = tokenizer.decode(generated)
+    print(resulting_string)
+This outputs a (hopefully) coherent string from the original sequence, as the
+:func:`~transformers.PreTrainedModel.generate` samples from a top_p/tok_k distribution:
+::
+    Hugging Face is based in DUMBO, New York City, and is a live-action TV series based on the novel by John
+    Carpenter, and its producers, David Kustlin and Steve Pichar. The film is directed by!
+Named Entity Recognition
+----------------------------------------------------
+Named Entity Recognition (NER) is the task of classifying tokens according to a class, for example identifying a
+token as a person, an organisation or a location.
+An example of a named entity recognition dataset is the CoNLL-2003 dataset, which is entirely based on that task.
+If you would like to fine-tune a model on an NER task, you may leverage the `ner/run_ner.py` (PyTorch),
+`ner/run_pl_ner.py` (leveraging pytorch-lightning) or the `ner/run_tf_ner.py` (TensorFlow) scripts.
+Here is an example using the pipelines do to named entity recognition, trying to identify tokens as belonging to one
+of 9 classes:
+- O, Outside of a named entity
+- B-MIS, Beginning of a miscellaneous entity right after another miscellaneous entity
+- I-MIS, Miscellaneous entity
+- B-PER, Beginning of a person's name right after another person's name
+- I-PER, Person's name
+- B-ORG, Beginning of an organisation right after another organisation
+- I-ORG, Organisation
+- B-LOC, Beginning of a location right after another location
+- I-LOC, Location
+It leverages a fine-tuned model on CoNLL-2003, fine-tuned by `@stefan-it <https://github.com/stefan-it>`__ from
+`dbmdz <https://github.com/dbmdz>`__.
+::
+    from transformers import pipeline
+    nlp = pipeline("ner")
+    sequence = "Hugging Face Inc. is a company based in New York City. Its headquarters are in DUMBO, therefore very" \
+               "close to the Manhattan Bridge which is visible from the window."
+    print(nlp(sequence))
+This outputs a list of all words that have been identified as an entity from the 9 classes defined above. Here is the
+expected results:
+::
+    [
+        {'word': 'Hu', 'score': 0.9995632767677307, 'entity': 'I-ORG'},
+        {'word': '##gging', 'score': 0.9915938973426819, 'entity': 'I-ORG'},
+        {'word': 'Face', 'score': 0.9982671737670898, 'entity': 'I-ORG'},
+        {'word': 'Inc', 'score': 0.9994403719902039, 'entity': 'I-ORG'},
+        {'word': 'New', 'score': 0.9994346499443054, 'entity': 'I-LOC'},
+        {'word': 'York', 'score': 0.9993270635604858, 'entity': 'I-LOC'},
+        {'word': 'City', 'score': 0.9993864893913269, 'entity': 'I-LOC'},
+        {'word': 'D', 'score': 0.9825621843338013, 'entity': 'I-LOC'},
+        {'word': '##UM', 'score': 0.936983048915863, 'entity': 'I-LOC'},
+        {'word': '##BO', 'score': 0.8987102508544922, 'entity': 'I-LOC'},
+        {'word': 'Manhattan', 'score': 0.9758241176605225, 'entity': 'I-LOC'},
+        {'word': 'Bridge', 'score': 0.990249514579773, 'entity': 'I-LOC'}
+    ]
+Note how the words "Hugging Face" have been identified as an organisation, and "New York City", "DUMBO" and
+"Manhattan Bridge" have been identified as locations.
+Here is an example doing named entity recognition using a model and a tokenizer. The process is the following:
+- Instantiate a tokenizer and a model from the checkpoint name. The model is identified as a BERT model and
+  loads it with the weights stored in the checkpoint.
+- Define the label list with which the model was trained on.
+- Define a sequence with known entities, such as "Hugging Face" as an organisation and "New York City" as a location.
+- Split words into tokens so that they can be mapped to the predictions. We use a small hack by firstly completely
+  encoding and decoding the sequence, so that we're left with a string that contains the special tokens.
+- Encode that sequence into IDs (special tokens are added automatically).
+- Retrieve the predictions by passing the input to the model and getting the first output. This results in a
+  distribution over the 9 possible classes for each token. We take the argmax to retrieve the most likely class
+  for each token.
+- Zip together each token with its prediction and print it.
+::
+    ## PYTORCH CODE
+    from transformers import AutoModelForTokenClassification, AutoTokenizer
+    import torch
+    model = AutoModelForTokenClassification.from_pretrained("dbmdz/bert-large-cased-finetuned-conll03-english")
+    tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")
+    label_list = [
+        "O",       # Outside of a named entity
+        "B-MISC",  # Beginning of a miscellaneous entity right after another miscellaneous entity
+        "I-MISC",  # Miscellaneous entity
+        "B-PER",   # Beginning of a person's name right after another person's name
+        "I-PER",   # Person's name
+        "B-ORG",   # Beginning of an organisation right after another organisation
+        "I-ORG",   # Organisation
+        "B-LOC",   # Beginning of a location right after another location
+        "I-LOC"    # Location
+    ]
+    sequence = "Hugging Face Inc. is a company based in New York City. Its headquarters are in DUMBO, therefore very" \
+               "close to the Manhattan Bridge."
+    # Bit of a hack to get the tokens with the special tokens
+    tokens = tokenizer.tokenize(tokenizer.decode(tokenizer.encode(sequence)))
+    inputs = tokenizer.encode(sequence, return_tensors="pt")
+    outputs = model(inputs)[0]
+    predictions = torch.argmax(outputs, dim=2)
+    print([(token, label_list[prediction]) for token, prediction in zip(tokens, predictions[0].tolist())])
+    ## TENSORFLOW CODE
+    from transformers import TFAutoModelForTokenClassification, AutoTokenizer
+    import tensorflow as tf
+    model = TFAutoModelForTokenClassification.from_pretrained("dbmdz/bert-large-cased-finetuned-conll03-english")
+    tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")
+    label_list = [
+        "O",       # Outside of a named entity
+        "B-MISC",  # Beginning of a miscellaneous entity right after another miscellaneous entity
+        "I-MISC",  # Miscellaneous entity
+        "B-PER",   # Beginning of a person's name right after another person's name
+        "I-PER",   # Person's name
+        "B-ORG",   # Beginning of an organisation right after another organisation
+        "I-ORG",   # Organisation
+        "B-LOC",   # Beginning of a location right after another location
+        "I-LOC"    # Location
+    ]
+    sequence = "Hugging Face Inc. is a company based in New York City. Its headquarters are in DUMBO, therefore very" \
+               "close to the Manhattan Bridge."
+    # Bit of a hack to get the tokens with the special tokens
+    tokens = tokenizer.tokenize(tokenizer.decode(tokenizer.encode(sequence)))
+    inputs = tokenizer.encode(sequence, return_tensors="tf")
+    outputs = model(inputs)[0]
+    predictions = tf.argmax(outputs, axis=2)
+    print([(token, label_list[prediction]) for token, prediction in zip(tokens, predictions[0].numpy())])
+This outputs a list of each token mapped to their prediction. Differently from the pipeline, here every token has
+a prediction as we didn't remove the "0" class which means that no particular entity was found on that token. The
+following array should be the output:
+::
+    [('[CLS]', 'O'), ('Hu', 'I-ORG'), ('##gging', 'I-ORG'), ('Face', 'I-ORG'), ('Inc', 'I-ORG'), ('.', 'O'), ('is', 'O'), ('a', 'O'), ('company', 'O'), ('based', 'O'), ('in', 'O'), ('New', 'I-LOC'), ('York', 'I-LOC'), ('City', 'I-LOC'), ('.', 'O'), ('Its', 'O'), ('headquarters', 'O'), ('are', 'O'), ('in', 'O'), ('D', 'I-LOC'), ('##UM', 'I-LOC'), ('##BO', 'I-LOC'), (',', 'O'), ('therefore', 'O'), ('very', 'O'), ('##c', 'O'), ('##lose', 'O'), ('to', 'O'), ('the', 'O'), ('Manhattan', 'I-LOC'), ('Bridge', 'I-LOC'), ('.', 'O'), ('[SEP]', 'O')]