Update backend/query_llm.py

backend/query_llm.py

@@ -15,8 +15,8 @@ import gradio as gr
 #from gradio_multimodalchatbot import MultimodalChatbot
 from gradio.data_classes import FileData
 
-tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
-#tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1")
+#tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1")
 # temperature = 0.2
 # #top_p = 0.6
 # repetition_penalty = 1.0
@@ -31,15 +31,15 @@ genai.configure(api_key=GOOGLE_API_KEY)
 OPENAI_KEY = getenv("OPENAI_API_KEY")
 HF_TOKEN = getenv("HUGGING_FACE_HUB_TOKEN")
 
-hf_client = InferenceClient(
-        "mistralai/Mistral-7B-Instruct-v0.1",
-        token=HF_TOKEN
-        )
-
 # hf_client = InferenceClient(
-#         "mistralai/Mixtral-8x7B-Instruct-v0.1",
+#         "mistralai/Mistral-7B-Instruct-v0.1",
 #         token=HF_TOKEN
 #         )
+
+hf_client = InferenceClient(
+        "mistralai/Mixtral-8x7B-Instruct-v0.1",
+        token=HF_TOKEN
+        )
 def format_prompt(message: str, api_kind: str):
     """
     Formats the given message using a chat template.