Update app/llm.py

app/llm.py

@@ -25,6 +25,17 @@ from langchain_core.runnables import RunnablePassthrough, RunnablePick
 rag_prompt_llama = hub.pull("rlm/rag-prompt-llama")
 rag_prompt.messages
 
+llm = llama_cpp.Llama.from_pretrained(
+    repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
+    filename="*q4_0.gguf",
+    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B-Chat"),
+    verbose=False,
+     n_ctx=512,
+     n_gpu_layers=0,
+    #chat_format="llama-2"
+)
+
+
 class RagChat:
     def agent(self): 
         loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
@@ -69,6 +80,7 @@ class ChatModel(BaseModel):
     mirostat_mode: int=2
     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",