Update app.py

app.py

@@ -22,41 +22,17 @@ import streamlit as st
 import requests
 import torch
 from transformers import pipeline
+from transformers import T5ForConditionalGeneration, T5Tokenizer
 
-# Function to download the model from Google Drive using requests
-def download_file_from_drive(file_id, output_path):
-    url = f'https://drive.google.com/uc?export=download&id={file_id}'
-    response = requests.get(url, stream=True)
-    
-    if response.status_code == 200:
-        with open(output_path, 'wb') as f:
-            for chunk in response.iter_content(chunk_size=8192):
-                if chunk:
-                    f.write(chunk)
-    else:
-        raise Exception(f"Failed to download file: Status code {response.status_code}")
-
-# Replace 'YOUR_FILE_ID' with the actual file ID of your model
-file_id = '1A2B3C4D5E6F7G8H9I0J'
-output_path = 'model.pt'
-
-# Download the model file
-try:
-    download_file_from_drive(file_id, output_path)
-except Exception as e:
-    st.error(f"Error downloading file: {e}")
-    st.stop()
+# Replace with your Hugging Face model repository path
+model_repo_path = 'AbdurRehman313/T5_samsum'
 
-# Load the model
-try:
-    model = torch.load(output_path)
-    model.eval()
-except Exception as e:
-    st.error(f"Error loading model: {e}")
-    st.stop()
+# Load the model and tokenizer
+model = T5ForConditionalGeneration.from_pretrained(model_repo_path)
+tokenizer = T5Tokenizer.from_pretrained(model_repo_path)
 
 # Initialize the summarization pipeline
-summarizer = pipeline('summarization', model=model)
+summarizer = pipeline('summarization', model=model,tokenizer=tokenizer)
 
 # Streamlit app layout
 st.title("Text Summarization App")