Was using byte position for end of offset, but it seems like using char position is correct

Author: Max Hniebergall

x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/nlp/tokenizers/UnigramTokenizer.java

@@ -368,7 +368,7 @@ List<DelimitedToken.Encoded> tokenize(CharSequence inputSequence, IntToIntFuncti
                             Strings.format("<0x%02X>", bytes[i]),
                             pieces[i],
                             offsetCorrection.apply(node.startsAtCharPos),
-                            offsetCorrection.apply(startsAtBytes + i)
+                            offsetCorrection.apply(node.startsAtCharPos + i)
                         )
                     );
                 }