Update README.md

README.md

@@ -65,6 +65,8 @@ The model learns to project it's learned dense representations over a MLM head t
   
 </details>
 
+## **[Skip to "HOW TO USE with POPULAR VECTORDBs and more"](#htu) or continue for more details.**
+
 
 ## 2. Motivation:
 SPLADE models are a fine balance between retrieval effectiveness (quality) and retrieval efficiency (latency and $), with that in mind we did **very minor retrieval efficiency tweaks** to make it more suitable for a industry setting. 
@@ -81,7 +83,6 @@ SPLADE models are a fine balance between retrieval effectiveness (quality) and r
 
 *Note: The paper refers to the best performing models as SPLADE++, hence for consistency we are reusing the same.*
 
-[**JUMP TO "USAGE" to try it out**](#htu) or continue for more details.
 
 <br/>
 
@@ -161,7 +162,11 @@ Ofcourse if it doesnt matter you could always use these models with Huggingface
 <h1 id="htu">How to use? </h1>
 
 
-## 7. With SPLADERunner Library
+## 6a. With Popular VectorDBs
+   - With Pinecone - [![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1fB6LheD9wYG0G-nBHiz0z2juvljrsBum?usp=sharing)
+   - With Qdrant - [![](https://colab.research.google.com/assets/colab-badge.svg)]()
+
+## 6b. With SPLADERunner Library
 
 [SPLADERunner Library](https://github.com/PrithivirajDamodaran/SPLADERunner)
 
@@ -180,7 +185,7 @@ sparse_rep = expander.expand(
 
  
 
-## 8. With HuggingFace
+## 6c. With HuggingFace
 
 **NOTEBOOK user? Login first**