Change model to zephyr

rag.py

@@ -22,13 +22,13 @@ NEO4J_PASSWORD = os.getenv("NEO4J_PASSWORD")
 vector_index = os.getenv("VECTOR_INDEX")
 
 chat_llm = HuggingFaceEndpoint(
-    repo_id="meta-llama/Meta-Llama-3-8B-Instruct",
+    repo_id="HuggingFaceH4/zephyr-7b-beta",
     task="text-generation",
     max_new_tokens=4096,
     do_sample=False,
 )
 
-global_tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
+# global_tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
 
 
 def local_retriever(query: str):
@@ -276,9 +276,8 @@ def global_retriever(query: str, level: int, response_type: str):
         i += 1
 
     ###Debug####
-
-    tokens = global_tokenizer(intermediate_results)
-    print(f"Number of input tokens: {len(tokens)}")
+    # tokens = global_tokenizer(intermediate_results)
+    # print(f"Number of input tokens: {len(tokens)}")
     ###Debug###
     final_response = reduce_chain.invoke(
         {