Update app.py

app.py

@@ -15,7 +15,7 @@ from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
 
 
-llm = Llama(model_path= hf_hub_download(repo_id="TheBloke/Llama-2-7B-32K-Instruct-GGUF", filename="llama-2-7b-32k-instruct.Q2_K.gguf"), n_ctx=2048) #download model from hf/ n_ctx=2048 for high ccontext length
+llm = Llama(model_path= hf_hub_download(repo_id="TheBloke/Llama-2-7B-32K-Instruct-GGUF", filename="llama-2-7b-32k-instruct.Q4_K_M.gguf"), n_ctx=2048) #download model from hf/ n_ctx=2048 for high ccontext length
 
 history = []