updated

app.py

@@ -5,14 +5,9 @@ import numpy as np
 
 
 # Define the function for sentiment analysis
-@st.cache_resource()
 
-def get_model():
-   # Load the model and tokenizer
-    tokenizer = AutoTokenizer.from_pretrained("xlnet-base-cased")
-    model = AutoModelForSequenceClassification.from_pretrained("MrDdz/mytuned_test_trainer-base-cased1")
-    return tokenizer,model
-tokenizer, model = get_model()
+
+
 
 # # Setting the page configurations
 # st.set_page_config(
@@ -66,6 +61,15 @@ unsafe_allow_html=True
 #     else:
 #         st.warning(f"The sentiment is {sentiment} with a score of {score*100:.2f}%!")
 
+
+@st.cache_resource()
+def get_model():
+   # Load the model and tokenizer
+    tokenizer = AutoTokenizer.from_pretrained("xlnet-base-cased")
+    model = AutoModelForSequenceClassification.from_pretrained("MrDdz/mytuned_test_trainer-base-cased1")
+    return tokenizer,model
+tokenizer, model = get_model()
+
 if text:
     text_sample = tokenizer([text], padding = True, Truncation = True, max_length = 512, return_tensors = 'pt' )
     output = model(** text_sample)