Update app.py

app.py

@@ -14,7 +14,7 @@ def predict(message, history):
     inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)  
     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("<|start_header_id|>assistant<|end_header_id|>\n\n")[-1].split("<|end_of_text|>")[0]
+    response = decoded.split("<|start_header_id|>assistant<|end_header_id|>\n\n")[-1]
     return response
 
 demo = gr.ChatInterface(predict, type="messages")