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-ai-q2_k",
-    filename="healthcare-ai-q2_k-unsloth.Q2_k.gguf",
+    filename="*.gguf",
     #tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-ai-q8_0"),
     verbose=False,
      n_ctx=4096,