fixes (#68)

- updates (59ea36cbfd76d707e96185f3462835606be09063)

dist/distill.bundle.js

@@ -2146,7 +2146,7 @@ function _arrayWithHoles(r) { if (Array.isArray(r)) return r; }
   function bylineTemplate(frontMatter) {
     return "\n    <div class=\"byline grid\">\n      <div>\n          <h3>Authors</h3>\n          <div>\n              ".concat(frontMatter.authors.map(function (author, i) {
       return "\n              <span class=\"author\">\n        ".concat(author.personalURL ? "\n          <a class=\"name\" href=\"".concat(author.personalURL, "\">").concat(author.name) + (i + 1 < frontMatter.authors.length ? "," : "") + "</a>" : "\n          <span class=\"name\">".concat(author.name) + (i + 1 < frontMatter.authors.length ? "," : "") + "</span>", "\n      </span>\n              ");
-    }).join(''), "\n          </div>\n      </div>\n      <div >\n          <h3>Affiliation</h3>\n          <div><a href=\"https://huggingface.co/\">HuggingFace</a>\n          </div>\n      </div>\n      <div >\n          <h3>Published</h3>\n          <div>Feb 19, 2025</div>\n      </div>\n    </div>\n");
+    }).join(''), "\n          </div>\n      </div>\n      <div >\n          <h3>Affiliation</h3>\n          <div><a href=\"https://huggingface.co/\">Hugging Face</a>\n          </div>\n      </div>\n      <div >\n          <h3>Published</h3>\n          <div>Feb 19, 2025</div>\n      </div>\n    </div>\n");
   }
   var Byline = /*#__PURE__*/function (_HTMLElement4) {
     function Byline() {

src/distill.js

@@ -2097,7 +2097,7 @@ d-appendix > distill-appendix {
       </div>
       <div >
           <h3>Affiliation</h3>
-          <div><a href="https://huggingface.co/">HuggingFace</a>
+          <div><a href="https://huggingface.co/">Hugging Face</a>
           </div>
       </div>
       <div >

src/index.html

@@ -1381,7 +1381,7 @@
         
         <ol>
             <li>Send “current keys and values” to the next machine except during the last time step in a non-blocking manner so we can starts the following step before this step is finished</li>
-            <li>Locally compute the attention score on the “current keys and values” it already has, which typically involves performing  <d-math>Softmax(\frac{QK^T}{\sqrt{d}}) * V</d-math>d-math>.</li>
+            <li>Locally compute the attention score on the “current keys and values” it already has, which typically involves performing  <d-math>Softmax(\frac{QK^T}{\sqrt{d}}) * V</d-math>.</li>
             <li>Wait to receive keys and values from the previous GPU and then circle back to step 1. where “current keys and values” are now the key/values just received from the previous GPU.</li>
         </ol>