Update app.py

app.py

@@ -17,7 +17,7 @@ retriever = RagRetriever.from_pretrained("facebook/rag-sequence-nq", index_name=
 rag_model = RagSequenceForGeneration.from_pretrained('facebook/rag-sequence-nq', retriever=retriever)
 rag_model.retriever.init_retrieval()
 rag_model.to(device)
-model = AutoModelForCausalLM.from_pretrained('google/gemma-2-2b-it',
+model = AutoModelForCausalLM.from_pretrained('HuggingFaceH4/zephyr-7b-beta',
                               device_map = 'auto',
                               torch_dtype = torch.bfloat16,
                              )
@@ -73,7 +73,7 @@ def retrieved_info(query, rag_model = rag_model, generating_model = model):
     generation_model_input = input_format(query, retrieved_context)
 
     # Generating answer using gemma model
-    tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b-it")
+    tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
     input_ids = tokenizer(generation_model_input, return_tensors='pt').to(device)
     output = generating_model.generate(input_ids, max_new_tokens = 512)