Update app/llm.py

app/llm.py

@@ -40,7 +40,7 @@ llm_chat = llama_cpp.Llama.from_pretrained(
 llm_generate = llama_cpp.Llama.from_pretrained(
     repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
     filename="*q4_0.gguf",
-    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B-Chat-GGUF"),
+    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B-Chat"),
     verbose=False,
      n_ctx=4096,
      n_gpu_layers=0,