update readme

README.md

@@ -1 +1,14 @@
 This model takes a tweet with the word "jew" in it, and determines if it's antisemitic.
+
+*Labels:*
+
+1 for antisemitic
+0 otherwise
+
+*Training data:*
+
+This model was trained on 4k tweets, where ~50% were labeled as antisemitic.
+
+*Disclaimer:*
+
+This model is not ready for production, it needs more evaluation and more training data.

README.md'

@@ -0,0 +1,8 @@
+This model takes a tweet with the word "jew" in it, and determines if it's antisemitic.
+
+Labels:
+
+1 for antisemitic
+0 otherwise
+
+NOTE: this model was trained on data that I labeled personally, with 4k tweets (~%50 antisemitic and ~50% not antisemitic).