chore: simplify

app.py

@@ -65,12 +65,11 @@ examples = [
 def predict(message, history):
     history.append({"role": "system", "content": system_prompt})
     history.append({"role": "user", "content": message})
-    input_text = tokenizer.apply_chat_template(history, tokenize=False)
-    inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)  
-    outputs = model.generate(inputs, max_new_tokens=100, temperature=0.2, top_p=0.9, do_sample=True)
-    decoded = tokenizer.decode(outputs[0])
-    response = decoded.split("<|im_start|>assistant\n")[-1].split("<|im_end|>")[0]
-    # response:  I'm ready to help you with your math homework. What's your math problem?
+
+    inputs = tokenizer.apply_chat_template(history, return_tensors="pt").to(device)
+    outputs = model.generate(**inputs, max_new_tokens=100)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
     print(f"Response: {response}, outputs: {outputs}")
     return response