Update app/llm.py

app/llm.py

@@ -41,7 +41,7 @@ llm_chat = llama_cpp.Llama.from_pretrained(
 llm_generate = llama_cpp.Llama.from_pretrained(
     repo_id="moriire/healthcare-GGUF",
     filename="healthcare-GGUF-unsloth.Q4_K_M.gguf",
-    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-GGUF")
+    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-GGUF"),
     verbose=False,
      n_ctx=4096,
      n_gpu_layers=0,