Update app.py

app.py

@@ -1,45 +1,32 @@
 import gradio as gr
-from transformers import pipeline, AutoModelForSeq2SeqLM, AutoTokenizer
+from transformers import pipeline, BartForConditionalGeneration, BartTokenizer
 import torch
 
-# 1. Setup
+# 1. Configuration
 MODEL_ID = "VoltIC/Automated-Text-Summarizer"
 SUBFOLDER = "summarizer_model"
 
-# 2. Initialization (No 'try' block here so we can see the real error in logs)
-print("🚀 Phase 1: Loading Tokenizer...")
-tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, subfolder=SUBFOLDER)
+print("🚀 Phase 1: Loading BART-specific Tokenizer...")
+# We use BartTokenizer directly to bypass the config.json check
+tokenizer = BartTokenizer.from_pretrained(MODEL_ID, subfolder=SUBFOLDER)
 
-print("🚀 Phase 2: Loading Model Weights (1.6GB)...")
-model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_ID, subfolder=SUBFOLDER)
+print("🚀 Phase 2: Loading BART Weights...")
+model = BartForConditionalGeneration.from_pretrained(MODEL_ID, subfolder=SUBFOLDER)
 
 print("🚀 Phase 3: Building Pipeline...")
-# This defines the 'summarizer' variable globally
 summarizer = pipeline(
     "summarization", 
     model=model, 
     tokenizer=tokenizer,
     framework="pt",
-    device=-1 # Forces CPU
+    device=-1
 )
-print("✅ SUCCESS: Summarizer is now defined!")
+print("✅ SUCCESS: Summarizer Ready!")
 
-# 3. Logic
 def summarize_text(text):
-    if not text:
-        return "Please enter text."
-    
-    # We use the global 'summarizer' defined above
+    if not text: return "Input empty."
     results = summarizer(text, max_length=100, min_length=30, truncation=True)
     return results[0]['summary_text']
 
-# 4. Interface
-demo = gr.Interface(
-    fn=summarize_text,
-    inputs=gr.Textbox(lines=10, label="Input Text"),
-    outputs=gr.Textbox(label="Summary"),
-    title="AI Text Summarizer"
-)
-
-if __name__ == "__main__":
-    demo.launch()
+demo = gr.Interface(fn=summarize_text, inputs="textbox", outputs="textbox")
+demo.launch()