Update app.py

app.py

@@ -5,14 +5,7 @@ import os
 import requests
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
-
-
-client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
-
-# Load the model and tokenizer
-model_name = "mistralai/Mixtral-8x7B-Instruct-v0.1"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+from huggingface_hub import InferenceClient, HfApi
 
 # If you have a GPU, move the model to it
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -50,8 +43,12 @@ class InferenceClient:
     def get_endpoint_metrics(self, repo_id, handler_path):
         pass
 
+client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
-from huggingface_hub import InferenceClient,HfApi
+# Load the model and tokenizer
+model_name = "mistralai/Mixtral-8x7B-Instruct-v0.1"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 # Define input prompt
 input_prompt = "(input value = highest-level-quality code content invocation ; True)"