Update README.md

README.md

@@ -44,9 +44,9 @@ pipeline_tag: sentence-similarity
     - [With Sentence Transformers:](#with-sentence-transformers)
     - [With Huggingface Transformers:](#with-huggingface-transformers)
 - [FAQs](#faqs)
-    - [How can we run these models with out heavy torch dependency?](#how-can-we-run-these-models-with-out-heavy-torch-dependency)
-    - [How do I optimise vector index cost?](#how-do-i-optimise-vector-index-cost)
-    - [How do I offer hybrid search to address Vocabulary Mismatch Problem?](#how-do-i-offer)
+    - [How can I reduce overall inference cost ?](#how-can-i-reduce-overall-inference-cost)
+    - [How do I reduce vector storage cost?](#how-do-i-reduce-vector-storage-cost)
+    - [How do I offer hybrid search to improve accuracy?](#how-do-i-offer-hybrid-search-to-improve-accuracy)
     - [Why not run MTEB?](#why-not-run-mteb)
 - [Roadmap](#roadmap)
 - [Notes on Reproducing:](#notes-on-reproducing)
@@ -143,13 +143,13 @@ for query, query_embedding in zip(queries, query_embeddings):
 
 # FAQS
 
-#### How can we run these models with out heavy torch dependency?
+#### How can I reduce overall inference cost ?
 - You can use ONNX flavours of these models via [FlashRetrieve](https://github.com/PrithivirajDamodaran/FlashRetrieve) library.
 
-#### How do I optimise vector index cost ? 
+#### How do I reduce vector storage cost ?
 [Use Binary and Scalar Quantisation](https://huggingface.co/blog/embedding-quantization)
 
-<h4>How do I offer hybrid search to address Vocabulary Mismatch Problem?</h4>
+#### How do I offer hybrid search to improve accuracy ?
 MIRACL paper shows simply combining BM25 is a good starting point for a Hybrid option: 
 The below numbers are with mDPR model, but miniMiracle_te_v1 should give a even better hybrid performance.