updating one line and adding in human eval to GPT4

README.md

@@ -48,7 +48,7 @@ Bloom chat should NOT be used for:
 - Mission-critical applications
 - Applications that involve the safety of others
 - Making highly important decisions
-- Important automated pipelines/decisions
+- Important automated pipelines
 
 This model is still in early development and can be prone to mistakes and hallucinations, there is still room for improvement. This model is intended to provide the community with a good baseline.
 
@@ -162,9 +162,15 @@ In the nucleus of atoms, protons and neutrons are bound together in a structure
 </figure>
 <br>
 
+![Human evaluation against GPT4](images/Human_evaluation_gpt4.png)
+<figure style="text-align:center;">
+    <figcaption><b>BLOOMChat vs GPT-4 in Human Preference Ranking</b></figcaption>
+</figure>
+<br>
+
 ![Multilingual evaluation](images/Multilingual_capabilities_comparison.png)
 <figure style="text-align:center;">
-    <figcaption><b>BLOOMChat surpasses other Bloom variants and state-of-the-art open-source chat models in translation setting</b></figcaption>
+    <figcaption><b>BLOOMChat surpasses other Bloom variants and state-of-the-art open-source chat models in translation tasks</b></figcaption>
 </figure>
 <br>