Update app.py

app.py

@@ -10,7 +10,7 @@ model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
 @spaces.GPU(duration=120)
 def predict(message, history):
     history.append({"role": "user", "content": message})
-    input_text = tokenizer.apply_chat_template(history, tokenize=False) + "<|assistant|>"
+    input_text = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True)
     inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)  
     outputs = model.generate(inputs, max_new_tokens=1024, temperature=0.7, top_p=0.9, do_sample=True)
     decoded = tokenizer.decode(outputs[0])