Update README.md

README.md

@@ -4,6 +4,7 @@ language:
 - en
 datasets:
 - Open-Orca/SlimOrca-Dedup
+pipeline_tag: question-answering
 ---
 # cosmosage
 
@@ -53,6 +54,6 @@ ASSISTANT:
 
 cosmosage_v0.2 performs much better than cosmosage_v0.1. While v0.1 did not seem to have picked up much knowledge from the ArXiV papers it was trained on, v0.2 can often give surprisingly good answers to highly technical questions about cosmology. It gives certain answers which it could not have known without having read these recent papers, leading me to conclude that it has learned knowledge from the ArXiV papers. 
 
-I've also been impressed by cosmosage's knowledge about astronomy, as well as other branches of physics. However, in these areas it is less clear how much the performance is due to the pretraining of the Mistral model versus the fine-tuning I did. I included quite a bit of data from older textbooks, so it can make mistakes. For example, it sometimes thinks Pluto is a planet.
+I've also been impressed by cosmosage's knowledge about astronomy, as well as other branches of physics. However, in these areas it is less clear how much the performance is due to the pretraining of the Mistral model versus the fine-tuning I did.
 
-Currently, the main challenge of cosmosage_v0.2 lies in its _reliability_. In many of its answers it confidently makes incorrect statements that appear to be completely made up.
+Currently, the main area where cosmosage_v0.2 needs to be improved is its _reliability_. In many of its answers it confidently makes incorrect statements that appear to be completely made up. This means that the outputs of cosmosage_v0.2 should not be trusted but rather thought of as potential explanations, food for thought, or inspiration.