Update app.py

app.py

@@ -29,7 +29,7 @@ _patent_id = st.selectbox(
 
 
 # display abstract and claim
-@st.cache(persist=True)
+@st.cache_data
 def get_abs_claim(_patent_id):
     # get abstract and claim corresponding to this patent id
     _abstract = dataset_dict["train"][["patent_number"] == _patent_id]["abstract"]
@@ -38,20 +38,28 @@ def get_abs_claim(_patent_id):
 
 
 _abstract, _claim = get_abs_claim(_patent_id)
-st.write(_abstract)
-st.write(_claim)
+st.write(_abstract)  # display abstract
+st.write(_claim)  # display claims
 
-input_text = _abstract + _claim
 
 # model and tokenizer initialization
-tokenizer = AutoTokenizer.from_pretrained(language_model_path)
+@st.cache_resource
+def load_model(language_model_path):
+    tokenizer = AutoTokenizer.from_pretrained(language_model_path)
+    model = AutoModelForSequenceClassification.from_pretrained(language_model_path)
+    return tokenizer, model
+
+
+tokenizer, model = load_model(language_model_path)
+# input to our model
+input_text = _abstract + _claim
+# get tokens
 inputs = tokenizer(
     input_text,
     truncation=True,
     padding=True,
     return_tensors="pt",
 )
-model = AutoModelForSequenceClassification.from_pretrained(language_model_path)
 
 # get predictions
 id2label = {0: "REJECTED", 1: "ACCEPTED"}