updating website

NolanoOrg · Dec 14, 2023 · 92075e0 · 92075e0
1 parent e703856
commit 92075e0
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 9 deletions.
diff --git a/_layouts/product.html b/_layouts/product.html
@@ -12,16 +12,16 @@
 </div>
 
 
-<h2 style="text-align: center;color:black">Open Source libraries for running Foundation Models locally</h3>
+<!-- <h2 style="text-align: center;color:black">Open Source libraries for running Foundation Models locally</h3> -->
 
-<br>
+<!-- <br>
 <div class="strip">
 <div class="container pb-6 pb-md-10">
 
-    <div class="row justify-content-start">
+    <div class="row justify-content-start"> -->
     <!-- write something about the features of our extension -->
 
-    {% assign limit = site.home.limit_services | default: 2 %}
+    <!-- {% assign limit = site.home.limit_services | default: 2 %}
     {% for service in site.services limit: limit %}
     
     <div class="col-12 col-md-6 mb-2">
@@ -37,7 +37,6 @@ <h2 class="service-title">
             
             <p>{{ service.content | markdownify | strip_html | truncate: 350 }}
             </p>
-            <!-- Add video using canva for each content -->           
         </div>
 
         
@@ -52,7 +51,7 @@ <h2 class="service-title">
     </div>
 
     
-    {% endfor %}
+    {% endfor %} -->
     <br>
 
     <!-- <div style="position: relative; width: 70%; height: 0; padding-top: 39.2500%;

diff --git a/product_service.md b/product_service.md
@@ -19,10 +19,17 @@ At Nolano, we understand this and are thrilled to introduce Nolano’s Turbo LLM
 <br>
 <br>
 
+<div style="text-align: center;">
+    <img src="https://blog.nolano.ai/assets/img/posts/hi-NOLIN-main.png" alt="Join Beta" width="450" height="450">
+</div>
+Hindi is one of the most widely used languages, spoken by more than 600 Million people. It has a rich ancient history, deeply ingrained in culture and reflected in a large amount of literature. However, no open-source high-quality Hindi LLM was built so far, perhaps due to the relative scarcity of data available for training such models from scratch.
+
+To overcome this issue, our we continually train our Hindi model on top of the existing open-source LLMs that were pre trained primarily on English language, aiming to extend the capabilities of those models to the new language without forgetting the one learned before, and without having to incur the excessive cost of training such model from scratch on a large iid dataset containing mix of Hindi with the other pre-training data those models were already exposed to. However, previous works leading to models such as CodeLLaMa (which extended LLaMa for code generation) and LeoLM (which extended LLaMa for German Language) demonstrated that extending model to new domain comes at a cost of lower performance on original domain - the issue called “catastrophic forgetting” in continual learning literature - even with optimizer re-warming up.
 
-<!-- <div style="text-align: center;">
 
-    <a href="/contact" class="button">Contact Us for Beta</a> 
-</div> -->
+<div style="text-align: center;">
+
+    <a href="https://huggingface.co/nolanoAI/Hi-NOLIN-9B" class="button">Download Hi-NOLIN</a> 
+</div>