added new model refernce

app.py

@@ -52,8 +52,8 @@ docs=docsearch.similarity_search(query,k=1)
 callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
 # Verbose is required to pass to the callback manager
 
-model_name_or_path = "TheBloke/Llama-2-7B-Chat-GGUF"
-filename = "llama-2-7b-chat.Q4_K_M.gguf" # the model is in bin format
+model_name_or_path = "anakin87/gemma-2b-orpo-GGUF"
+filename = "gemma-2b-orpo.Q5_K_M.gguf" # the model is in bin format
 model_path = hf_hub_download(repo_id=model_name_or_path, filename=filename)
 
 n_gpu_layers = 40  # Change this value based on your model and your GPU VRAM pool.