Update app.py

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 = "princeton-nlp/Sheared-LLaMA-1.3B"
+model_id = "princeton-nlp/Sheared-LLaMA-2.7B"
 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)
 
@@ -250,6 +250,7 @@ def generate(
     query_embedding = create_query_embedding(condensed_query)
     relevant_chunks = find_nearest_neighbors(query_embedding)
     reranked_relevant_chunks = rerank_chunks_with_cross_encoder(condensed_query, relevant_chunks)
+    print(reranked_relevant_chunks)
     qa_prompt = create_qa_prompt(condensed_query, reranked_relevant_chunks)
     print(f"{qa_prompt=}")
     generator = get_completion(