Update app/llm.py

app/llm.py

@@ -39,8 +39,8 @@ llm_chat = llama_cpp.Llama.from_pretrained(
     #chat_format="llama-2"
 )
 llm_generate = 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=4096,
@@ -75,7 +75,7 @@ def health():
 # Chat Completion API
 @llm_router.post("/chat/", tags=["llm"])
 async def chat(chatm:ChatModel):#, user: schemas.BaseUser = fastapi.Depends(current_active_user)):
-    #chatm.system = chatm.system.format(user.email)
+    chatm.system = chatm.system.format("")#user.email)
     try:
         st = time()
         output = llm_chat.create_chat_completion(