Medium blog added

Author: Shekswess

README.md

@@ -9,7 +9,7 @@
 
 <p align="center">
   <a href="https://lokahq.github.io/Trinity-Mini-DrugProt-Think/">📝 <strong>Report</strong></a> &nbsp; | &nbsp;
-  <a href="https://medium.com/@jakimovski_bojan/9e1c1c430ce9">
+  <a href="https://medium.com/loka-engineering/deploying-trinity-mini-drugprot-think-on-amazon-sagemaker-ai-9e1c1c430ce9">
     <img
       src="https://www.sysgroup.com/wp-content/uploads/2025/02/Amazon_Web_Services-Logo.wine_.png"
       alt="AWS"

index.html

@@ -10,12 +10,12 @@
     <meta property="og:type" content="article" />
     <meta property="og:title" content="Post-Training an Open MoE Model to Extract Drug-Protein Relations: Trinity-Mini-DrugProt-Think" />
     <meta property="og:description" content="A practical ablation study: GRPO-style reinforcement learning with LoRA on Arcee Trinity Mini for DrugProt drug-protein relation extraction. We sweep LoRA alpha, learning rate, batch size, max tokens, temperature, and rollout budget to find what actually moves the needle." />
-	    <meta property="og:image" content="https://raw.githubusercontent.com/LokaHQ/Trinity-Mini-DrugProt-Think/main/assets/logo.png" />
+	  <meta property="og:image" content="https://raw.githubusercontent.com/LokaHQ/Trinity-Mini-DrugProt-Think/main/assets/logo.png" />
     <meta property="og:image:alt" content="TRINITY: Trinity-Mini-DrugProt-Think cover image." />
     <meta name="twitter:card" content="summary_large_image" />
     <meta name="twitter:title" content="Post-Training an Open MoE Model to Extract Drug-Protein Relations: Trinity-Mini-DrugProt-Think" />
     <meta name="twitter:description" content="A practical ablation study: GRPO-style reinforcement learning with LoRA on Arcee Trinity Mini for DrugProt drug-protein relation extraction. We sweep LoRA alpha, learning rate, batch size, max tokens, temperature, and rollout budget to find what actually moves the needle." />
-	    <meta name="twitter:image" content="https://raw.githubusercontent.com/LokaHQ/Trinity-Mini-DrugProt-Think/main/assets/logo.png" />
+	  <meta name="twitter:image" content="https://raw.githubusercontent.com/LokaHQ/Trinity-Mini-DrugProt-Think/main/assets/logo.png" />
     <title>Post-Training an Open MoE Model to Extract Drug-Protein Relations: Trinity-Mini-DrugProt-Think</title>
     <link rel="icon" type="image/svg+xml" href="https://cdn.prod.website-files.com/6490383845d4c0f51f929ca8/649052c9d3731fb704eea658_favicon.svg" />
     <script src="https://cdn.jsdelivr.net/npm/chart.js@4.4.7/dist/chart.umd.min.js"></script>
@@ -874,7 +874,7 @@ <h1 class="post-title">
 	          <ul class="resource-links">
 		            <li><a href="https://github.com/LokaHQ/Trinity-Mini-DrugProt-Think" aria-label="GitHub"><svg class="icon" viewBox="0 0 16 16" fill="currentColor"><path d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27s1.36.09 2 .27c1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.01 8.01 0 0 0 16 8c0-4.42-3.58-8-8-8z"/></svg></a></li>
 		            <li><a href="https://huggingface.co/lokahq/Trinity-Mini-DrugProt-Think" aria-label="HuggingFace"><img class="icon" src="https://huggingface.co/front/assets/huggingface_logo-noborder.svg" alt="HuggingFace" /></a></li>
-		            <li><a href="https://medium.com/@jakimovski_bojan/9e1c1c430ce9" aria-label="Deployment guide" title="Deployment guide"><img class="icon" src="https://www.sysgroup.com/wp-content/uploads/2025/02/Amazon_Web_Services-Logo.wine_.png" alt="AWS deployment guide" /></a></li>
+		            <li><a href="https://medium.com/loka-engineering/deploying-trinity-mini-drugprot-think-on-amazon-sagemaker-ai-9e1c1c430ce9" aria-label="Deployment guide" title="Deployment guide"><img class="icon" src="https://www.sysgroup.com/wp-content/uploads/2025/02/Amazon_Web_Services-Logo.wine_.png" alt="AWS deployment guide" /></a></li>
 	          </ul>
 	        </section>
 
@@ -1718,7 +1718,7 @@ <h2 id="conclusion">
 		            We have published the adapter weights (<a href="https://huggingface.co/lokahq/Trinity-Mini-DrugProt-Think"><strong>lokahq/Trinity-Mini-DrugProt-Think</strong></a>) and written a step-by-step deployment guide
 	            using the <strong>AWS SageMaker SDK v3</strong>, covering how to serve the merged
 	            model as a real-time endpoint:
-	            <a href="https://medium.com/@jakimovski_bojan/9e1c1c430ce9">deployment guide</a>.
+	            <a href="https://medium.com/loka-engineering/deploying-trinity-mini-drugprot-think-on-amazon-sagemaker-ai-9e1c1c430ce9">deployment guide</a>.
 	            SageMaker&rsquo;s managed inference handles scaling and hardware allocation;
 	            the guide walks through container selection, endpoint configuration, and a
             sample inference call against the DrugProt relation types.