Update app/llm.py

app/llm.py

@@ -33,7 +33,7 @@ llm_chat = llama_cpp.Llama.from_pretrained(
     filename="*q4_0.gguf",
     tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B-Chat"),
     verbose=False,
-     n_ctx=128,
+     n_ctx=512,
      n_gpu_layers=0,
     #chat_format="llama-2"
 )