Update app.py

app.py

@@ -12,9 +12,9 @@ def predict(message, history):
     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)
+    outputs = model.generate(inputs, max_new_tokens=100, temperature=0.7, 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 = decoded.split("<|start_header_id|>assistant<|end_header_id|>\\n\\n")[-1].split("<|im_end|>")[0]
     return response
 
 demo = gr.ChatInterface(predict, type="messages")