Update app.py

app.py

@@ -159,20 +159,19 @@ def query(system_prompt, user_prompt, temperature=0.9, max_new_tokens=256, top_p
     prompt = f"System: {system_prompt}\nUser: {user_prompt}\n"
     print(prompt)
     print('-----')
-    output = client.text_generation(prompt, **generate_kwargs, details=True, return_full_text=False)
-    print(output)
-    # stream = client.text_generation(prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    # output = ""
-
-    # for response in stream:
-    #     output += response.token.text
-
-    #     for stop_str in STOP_SEQUENCES:
-    #         if output.endswith(stop_str):
-    #             output = output[:-len(stop_str)]
-    #             output = output.rstrip()
-    #             yield output
-    #     yield output
+    #output = client.text_generation(prompt, **generate_kwargs, details=True, return_full_text=False)
+    #print(output)
+    stream = client.text_generation(prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    output = ""
+    for response in stream:
+        output += response.token.text
+
+        for stop_str in STOP_SEQUENCES:
+            if output.endswith(stop_str):
+                output = output[:-len(stop_str)]
+                output = output.rstrip()
+                #yield output
+        #yield output
     return output
 
 iface = gr.Interface(