Update app/llm.py

app/llm.py

@@ -30,8 +30,8 @@ class ChatModel(BaseModel):
     mirostat_tau: float=4.0
     mirostat_eta: float=1.1
 llm_chat = llama_cpp.Llama.from_pretrained(
-    repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
-    filename="*q4_0.gguf",
+    repo_id="moriire/healthcare-GGUF",
+    filename="*.gguf",
     tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B"),
     verbose=False,
      n_ctx=1024,