Update app.py

app.py

@@ -157,18 +157,20 @@ def query(system_prompt, user_prompt, temperature=0.9, max_new_tokens=256, top_p
         seed=seed,
     )
     prompt = f"System: {system_prompt}\nUser: {user_prompt}\n"
-    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
+    print(prompt)
+    output = client.text_generation(prompt, **generate_kwargs, details=True, return_full_text=False)
+    # 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(