Update app/llm.py

app/llm.py

@@ -31,7 +31,7 @@ class ChatModel(BaseModel):
     mirostat_eta: float=1.1
 llm_chat = 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=1024,