Update README.md

README.md

@@ -1,6 +1,9 @@
 ---
 tags:
 - intent, topic-discovery
+datasets:
+- tuetschek/atis
+- clinc/clinc_oos
 ---
 # Model Card for Model ID
 
@@ -116,10 +119,10 @@ Using HF trainer
 ## Evaluation
 
 <!-- This section describes the evaluation protocols and provides the results. -->
-The newest version of the model is finetuned on 2 synthetic datasets Atis dataset and parts of clinc_oos in a few shot manner.
-All datasets have 10-20 samples per class. 
+The newest version of the model is finetuned on 2 synthetic datasets and 41 first classes of clinc_oos in a few shot manner.
+All datasets have 10-20 samples per class. Training data did not include Atis dataset.
 
-Atis test set evaluation: weighted F1 90%
+Atis zero shot test set evaluation: weighted F1 87%
 Clinc test set is next.