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="moriire/healthcare-GGUF",
-    filename="*.gguf",
+    filename="healthcare-GGUF-unsloth.Q4_K_M.gguf",
     tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B"),
     verbose=False,
      n_ctx=4096,