Update README.md

README.md

@@ -131,6 +131,22 @@ This in turns allows our reranker to benefit from improvements to inference as a
 
 # How to use
 
+The model was trained to expect an input such as:
+
+```
+<<<Query>>>
+{your_query_here}
+
+<<<Context>>>
+{your_context_here}
+```
+
+And to output a string of a number between 1-7.
+
+In order to make a continuous score that can be used for reranking query-context pairs (i.e. a method with few ties), we calculate the expectation value of the scores.
+
+We include scripts to do this in both vLLM and LMDeploy:
+
 #### vLLM
 
 Install [vLLM](https://github.com/vllm-project/vllm/) using `pip install vllm`.
@@ -259,8 +275,12 @@ We make our evaluation code and results available [on our Github](https://github
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/P-XCA3TGHqDSX8k6c4hCE.png)
 
+As we can see, this reranker attains greater IR evaluation metrics compared to the two benchmarks we include for all positions apart from @1.
+
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/puhhWseBOcIyOEdW4L-B0.png)
 
+We also show that our model is, on average, faster than the BGE reranker v2.
+
 # License
 
 We share this model under an Apache 2.0 license.