Update app.py

app.py

@@ -21,7 +21,7 @@ client = InferenceClient(
 # Load pre-trained mixtral tokenizer model (replace with your desired model if you want)
 model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModel.from_pretrained(model_id)
+model = AutoModel.from_pretrained(model_id, load_in_4bit=True, use_flash_attention_2=True)
 
 # Function to convert text items into embeddings
 def get_embeddings(text_items):