Merge pull request #121 from premAI-io/email-validation

_static/emails.js

@@ -22,21 +22,15 @@ function getCookie(cname) {
 
 async function emailButtonClick() {
   let emailInput = document.getElementById("email-input");
-  let emailValue = emailInput.value;
-  let res = await fetch("https://premai.pythonanywhere.com/email?a=" + emailValue);
-  const ok = 200 <= res.status && res.status < 299;
-  const server_err = 500 <= res.status && res.status < 599;
-  if (ok || server_err) {
+  // from https://html.spec.whatwg.org/multipage/input.html#valid-e-mail-address
+  const valid = /^[a-zA-Z0-9.!#$%&'*+\/=?^_`{|}~-]+@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*$/;
+  if (valid.test(emailInput.value)) {
     let modal = document.getElementById('email-modal');
     modal.style.display = 'none';
-    emailInput.value = "";
+    setCookie("address", emailInput.value, 365); // might fail if cookies disabled
   } else {
     let emailError = document.getElementsByClassName('email-error')[0];
-    let msg = await res.json();
-    emailError.innerHTML = "Error " + res.status + ": " + msg.status;
-  }
-  if (ok) {
-    setCookie("address", emailValue, 365); // might fail if cookies disabled
+    emailError.innerHTML = "Error: please enter a valid email";
   }
 }
 

fine-tuning.md

@@ -144,7 +144,9 @@ Preparing a robust dataset is key to building a fine-tuned model. For audio rela
 
 The performance of a fine-tuned model largely depends on the **quality** and **quantity** of training data.
 
-For LLMs, the quantity of data can be an important factor when deciding whether to fine-tune or not. There have been many success stories of companies like Bloomberg {cite}`wu2023bloomberggpt`, [Mckinsey](https://www.mckinsey.com/about-us/new-at-mckinsey-blog/meet-lilli-our-generative-ai-tool), and [Moveworks](https://www.moveworks.com/insights/moveworks-enterprise-llm-benchmark-evaluates-large-language-models-for-business-applications) that have either created their own LLM or fine-tuned an existing LLM which has better performance than ChatGPT on certain tasks. However, tens of thousands of data points were required in order to make these successful AI bots and assistants. In the [Moveworks blog post](https://www.moveworks.com/insights/moveworks-enterprise-llm-benchmark-evaluates-large-language-models-for-business-applications), the fine-tuned model which surpasses the performance of GPT-4 on certain tasks, was trained on an internal dataset consisting of 70K instructions.
+For LLMs, the quantity of data can be an important factor when deciding whether to fine-tune or not. There have been many success stories of companies like Bloomberg {cite}`wu2023bloomberggpt`, [Mckinsey](https://www.mckinsey.com/about-us/new-at-mckinsey-blog/meet-lilli-our-generative-ai-tool), and [Moveworks] that have either created their own LLM or fine-tuned an existing LLM which has better performance than ChatGPT on certain tasks. However, tens of thousands of data points were required in order to make these successful AI bots and assistants. In the [Moveworks blog post][Moveworks], the fine-tuned model which surpasses the performance of GPT-4 on certain tasks, was trained on an internal dataset consisting of 70K instructions.
+
+[Moveworks]: https://www.moveworks.com/us/en/resources/blog/moveworks-enterprise-llm-benchmark-evaluates-large-language-models-for-business-applications
 
 In the case of computer vision models, data quality can play a significant role in the performance of the model. Andrew Ng, a prominent researcher and entrepreneur in the field of AI, has been an advocate of data centric AI in which the quality of the data is more important than the sheer volume of data {cite}`small-data-tds`.