change model to openchat/openchat_3.5

backend/query_llm.py

@@ -8,7 +8,7 @@ from typing import Any, Dict, Generator, List
 from huggingface_hub import InferenceClient
 from transformers import AutoTokenizer
 
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")  # model name
+tokenizer = AutoTokenizer.from_pretrained("openchat/openchat_3.5")  # model name
 
 temperature = 0.9
 top_p = 0.6
@@ -18,7 +18,7 @@ OPENAI_KEY = getenv("OPENAI_API_KEY")
 HF_TOKEN = getenv("HUGGING_FACE_HUB_TOKEN")
 
 hf_client = InferenceClient(
-        "meta-llama/Llama-2-7b-chat-hf",   
+        "openchat/openchat_3.5",   
         token=HF_TOKEN
         )