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/Dolphin-Llama2-7B-GGML", filename="dolphin-llama2-7b.ggmlv3.q4_1.bin"), n_ctx=2048) #download model from hf/ n_ctx=2048 for high ccontext length
+llm = Llama(model_path= hf_hub_download(repo_id="TheBloke/LlongOrca-7B-16K-GGUF", filename="llongorca-7b-16k.Q5_K_M.gguf"), n_ctx=2048) #download model from hf/ n_ctx=2048 for high ccontext length
 
 history = []