Update app.py

app.py

@@ -24,9 +24,23 @@ def test_models():
     for model in models:
         start_time = datetime.now()
         try:
+
+            generate_kwargs = dict(
+                temperature=temp,
+                max_new_tokens=tokens,
+                top_p=top_p,
+                repetition_penalty=rep_p,
+                do_sample=True,
+                seed=111111111,
+            )
+          
             print(f'trying: {model}\n')
             client= InferenceClient(model)
-            outp=client.text_generation("What is a cat",details=True, return_full_text=True)
+            outp=""
+            stream=client.text_generation("What is a cat", **generate_kwargs, stream=True, details=True, return_full_text=True)
+            for response in stream:
+                outp += response.token.text
+                print (outp)            
             time_delta = datetime.now() - start_time
             count=time_delta.total_seconds()
             #if time_delta.total_seconds() >= 180: