Create app.py

app.py

@@ -0,0 +1,40 @@
+import streamlit as st
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+# Load pre-trained model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("avisena/bart-base-job-info-summarizer")
+model = AutoModelForSeq2SeqLM.from_pretrained("avisena/bart-base-job-info-summarizer")
+
+# Streamlit app
+st.title("Text Summarization App")
+
+# Text input
+text_input = st.text_area("Enter the text to summarize:", height=200)
+
+# Summarize button
+if st.button("Summarize"):
+    if text_input:
+        # Tokenize input text
+        inputs = tokenizer.encode(text_input, return_tensors="pt", max_length=1024, truncation='do_not_truncate')
+
+        # Generate summary
+        summary_ids = model.generate(
+            inputs,
+            max_length=200,  # Maximum length of the summary
+            min_length=30,   # Minimum length of the summary
+            length_penalty=0.98,  # Penalty for longer sequences
+            num_beams=6,     # Number of beams for beam search
+            top_p=3.7,
+            early_stopping=True,
+            temperature=1.4,
+            do_sample=True
+        )
+
+        # Decode summary
+        summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True, max_length=512, truncation='do_not_truncate')
+
+        # Display the summarized text
+        st.subheader("Summary")
+        st.write(summary)
+    else:
+        st.warning("Please enter some text to summarize.")