Update README.md

README.md

@@ -4,6 +4,15 @@ datasets:
 - AbstractPhil/geometric-vocab
 pipeline_tag: zero-shot-classification
 ---
+# Zana the current version is quite small and quite fast
+At about 500k the zana_nano competes with it's big sister pixie at a superior accuracy rating AND produces image features.
+
+Running the system with refined wordnet tokens rather than full unicode made all the difference. The findings show that meaningful semantics matter a whole lot.
+
+unicode; 21%
+same model
+wordnet_eng; >42%
+
 
 # All losses modified heavily, the originals did not work at all with the structure.
 V3 incoming.