Update app.py

app.py

@@ -31,8 +31,8 @@ model_classes = {
 }
 
 
-# @st.cache(allow_output_mutation=True, suppress_st_warning=True)
-@st.cache_resource
+@st.cache(allow_output_mutation=True, suppress_st_warning=True)
+# @st.cache_resource
 def load_t5():
     model = AutoModelForSeq2SeqLM.from_pretrained("t5-base")
 
@@ -40,35 +40,35 @@ def load_t5():
     return model, tokenizer
 
 
-# @st.cache(allow_output_mutation=True, suppress_st_warning=True)
-@st.cache_resource
+@st.cache(allow_output_mutation=True, suppress_st_warning=True)
+# @st.cache_resource
 def custom_model():
     return pipeline("summarization", model="my_awesome_sum/")
 
 
-# @st.cache(allow_output_mutation=True, suppress_st_warning=True)
-@st.cache_resource
+@st.cache(allow_output_mutation=True, suppress_st_warning=True)
+# @st.cache_resource
 def convert_df(df):
     # IMPORTANT: Cache the conversion to prevent computation on every rerun
     return df.to_csv(index=False).encode("utf-8")
 
 
-# @st.cache(allow_output_mutation=True, suppress_st_warning=True)
-@st.cache_resource
+@st.cache(allow_output_mutation=True, suppress_st_warning=True)
+# @st.cache_resource
 def load_one_line_summarizer(model):
     return model.load_model("t5", "snrspeaks/t5-one-line-summary")
 
 
-# @st.cache(allow_output_mutation=True, suppress_st_warning=True)
-@st.cache_resource
+@st.cache(allow_output_mutation=True, suppress_st_warning=True)
+# @st.cache_resource
 def classify_category():
     tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
     new_model = load_model("model")
     return tokenizer, new_model
 
 
-# @st.cache(allow_output_mutation=True, suppress_st_warning=True)
-@st.cache_resource
+@st.cache(allow_output_mutation=True, suppress_st_warning=True)
+# @st.cache_resource
 def classify_sub_theme():
     tokenizer = BertTokenizer.from_pretrained(
         "ashhadahsan/amazon-subtheme-bert-base-finetuned"