Update app.py

app.py

@@ -2,7 +2,7 @@ import streamlit as st
 from transformers import pipeline, AutoTokenizer
 import torch
 
-# Define the model
+# model
 model = "facebook/bart-large-cnn"
 
 @st.cache_resource
@@ -10,18 +10,13 @@ def load_summarizer():
     return pipeline("summarization", model=model)
 
 def get_model_max_length(model_name):
-    try:
         tokenizer = AutoTokenizer.from_pretrained(model_name)
         return tokenizer.model_max_length
-    except:
-        return 1024  # default value if unable to determine
 
 def generate_summary(text):
     summarizer = load_summarizer()
     max_input_length = min(summarizer.tokenizer.model_max_length, 1024)
-    truncated_text = summarizer.tokenizer.decode(
-        summarizer.tokenizer.encode(text, truncation=True, max_length=max_input_length)
-    )
+    truncated_text = summarizer.tokenizer.decode(summarizer.tokenizer.encode(text, truncation=True, max_length=max_input_length))
     summary = summarizer(truncated_text, max_new_tokens=150, min_new_tokens=40, do_sample=False)[0]['summary_text']
     return summary
 
@@ -38,8 +33,6 @@ if st.button("Generate Summary"):
         st.subheader("Summary:")
         st.write(summary)
     else:
-        st.warning("Please enter some text to summarize.")
+        st.warning("Please enter text to summarize.")
 
-st.write("---")
-st.write("Model: facebook/bart-large-cnn")
-st.write(f"Max input length: {get_model_max_length(model)}")
+st.write("---")