Update README.md

README.md

@@ -5,12 +5,10 @@ tags:
 - text-classification
 - generated_from_setfit_trainer
 widget:
-- text: '
-
-    Ex-Labour Bennite in X detox. Pro-planet, anti-capitalist.'
+- text: 'Wonderful person aboard!'
 - text: jan o lukin ala e pilin sina.
 - text: Nothing…I’m just loudly complaining, I’ll get over it tomorrow.
-- text: IDIOT
+- text: HEY THERE
 - text: Pizza cutter 2
 metrics:
 - accuracy
@@ -65,7 +63,7 @@ The model has been trained using an efficient few-shot learning technique that i
 | Label     | Examples                                                                                                                                                                                                                                  |
 |:----------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | toki pona | <ul><li>'ona li toki "toki" tawa meli.'</li><li>'toki li pona tawa mi.'</li><li>'mi toki e ni tawa ona: "o kama tawa tomo mi."'</li></ul>                                                                                                 |
-| other     | <ul><li>'No te puedo creer el grado de precisión 🤣'</li><li>'i can’t deny i’m invested in the gaiartemis aspect of things :’)'</li><li>"I'm live on #twitch, and speedrunning EarthBound!\r\n\r\nhttps://twitch.tv/lordtacoTV "</li></ul> |
+| other     | <ul><li>'No te puedo creer el grado de precisión 🤣'</li><li>'i can’t deny i’m invested in the aspect of things :’)'</li><li>"I'm live on #twitch, and speedrunning EarthBound!"</li></ul> |
 
 ## Evaluation
 
@@ -92,7 +90,7 @@ from setfit import SetFitModel
 # Download from the 🤗 Hub
 model = SetFitModel.from_pretrained("johnpaulbin/toki-pona-classifier-v2")
 # Run inference
-preds = model("IDIOT")
+preds = model(["Hello!", "toki!"])
 ```
 
 <!--