Update app.py

app.py

@@ -151,7 +151,8 @@ if st.button("Send") and prompt.strip():
     inputs = tokenizer.apply_chat_template(
         chat,
         add_generation_prompt=True,
-        return_tensors="pt"
+        return_tensors="pt",
+        return_dict=True
     )
 
     streamer = TextIteratorStreamer(
@@ -161,15 +162,15 @@ if st.button("Send") and prompt.strip():
     )
 
     gen_kwargs = dict(
-        input_ids=inputs,
+        **inputs,
         max_new_tokens=MAX_NEW_TOKENS,
+        do_sample=True,
         temperature=TEMPERATURE,
         top_p=TOP_P,
-        do_sample=True,
-        streamer=streamer,
         eos_token_id=tokenizer.eos_token_id,
         pad_token_id=tokenizer.eos_token_id,
-    )
+        streamer=streamer
+        )
 
     thread = threading.Thread(target=model.generate, kwargs=gen_kwargs)
     thread.start()