Update app.py

app.py

@@ -72,14 +72,20 @@ def get_conversational_rag_chain(retriever_chain,llm):
     return create_retrieval_chain(retriever_chain, stuff_documents_chain)
 
 def get_response(user_input):
-    llm = CTransformers(
-                    # model = "TheBloke/Mistral-7B-Instruct-v0.2-GGUF",
-                    model= "TheBloke/Llama-2-7B-Chat-GGUF",
-                    model_file = "llama-2-7b-chat.Q3_K_S.gguf",
-                    model_type="llama",
-                    max_new_tokens = 300,
-                    temperature = 0.3,
-                    lib="avx2", # for CPU
+    # llm = CTransformers(
+    #                 # model = "TheBloke/Mistral-7B-Instruct-v0.2-GGUF",
+    #                 model= "TheBloke/Llama-2-7B-Chat-GGUF",
+    #                 model_file = "llama-2-7b-chat.Q3_K_S.gguf",
+    #                 model_type="llama",
+    #                 max_new_tokens = 300,
+    #                 temperature = 0.3,
+    #                 lib="avx2", # for CPU
+    # )
+
+    llm_model == "TinyLlama/TinyLlama-1.1B-Chat-v1.0":
+    llm = HuggingFaceHub(
+        repo_id=llm_model, 
+        model_kwargs={"temperature": temperature, "max_new_tokens": 250, "top_k": top_k}
     )
     retriever_chain = get_context_retriever_chain(st.session_state.vector_store,llm)
     conversation_rag_chain = get_conversational_rag_chain(retriever_chain,llm)