Update app.py

app.py

@@ -35,7 +35,7 @@ def respond(
     messages.append({"role": "user", "content": message})
     print(messages)
     inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True, enable_reasoning=enable_reasoning, return_dict=True).to(device)
-    generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=max_tokens, temperature=temperature, repetition_penalty=repetition_penalty, eos_token_id=tokenizer.convert_tokens_to_ids("<|im_end|>"))
+    generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=max_tokens, temperature=temperature, repetition_penalty=repetition_penalty)
     thread = Thread(target=model.generate, kwargs=generation_kwargs)
 
     thread.start()