Update README.md

This model is trained on the 'mcq' split of the microsoft/orca-agentinstruct-1M-v1 dataset. I tried to fine tune the model further for QA prompts specifically for mcq's.

README.md

@@ -1,3 +1,9 @@
----
-license: mit
----
+---
+license: mit
+datasets:
+- microsoft/orca-agentinstruct-1M-v1
+language:
+- en
+base_model:
+- unsloth/Phi-3.5-mini-instruct
+---