Change LLaMA2-70B to Sheared 1.3B

app.py

@@ -34,7 +34,7 @@ torch_device = "cuda" if torch.cuda.is_available() else "cpu"
 print("Running on device:", torch_device)
 print("CPU threads:", torch.get_num_threads())
 
-model_id = "meta-llama/Llama-2-70b-chat-hf"
+model_id = "princeton-nlp/Sheared-LLaMA-1.3B"
 biencoder = SentenceTransformer("intfloat/e5-large-v2", device=torch_device)
 cross_encoder = CrossEncoder("cross-encoder/ms-marco-MiniLM-L-12-v2", max_length=512, device=torch_device)