Update handler.py

handler.py

@@ -27,10 +27,10 @@ class EndpointHandler:
         # pass inputs with all kwargs in data
         if parameters is not None:
             with torch.autocast("cuda"):
-                outputs = self.model.generate(**inputs, **parameters)
+                outputs = self.model.generate(**inputs, **parameters, do_sample=True, guidance_scale=3)
         else:
             with torch.autocast("cuda"):
-                outputs = self.model.generate(**inputs,)
+                outputs = self.model.generate(**inputs, do_sample=True, guidance_scale=3, max_new_tokens=450)
 
         # postprocess the prediction
         prediction = outputs[0].cpu().numpy().tolist()