Update app.py

app.py

@@ -1,13 +1,11 @@
 import streamlit as st
-from transformers import AutoTokenizer, AutoModelForQuestionAnswering, pipeline
+from transformers import AutoTokenizer, AutoModelForQuestionAnswering
 
 # Load the model and tokenizer from your Hugging Face Hub repository
 model_checkpoint = "abdulllah01/checkpoints"  # Replace with your actual checkpoint
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
-model = AutoModelForQuestionAnswering.from_pretrained(model_checkpoint)
-
+model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)
 # Create a pipeline for question answering
-qa_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 # Streamlit UI setup
 st.title("Question Answering App")
@@ -18,12 +16,19 @@ context = st.text_area("Context:", "")
 
 # Text input for the question
 question = st.text_input("Question:", "")
+# Example input question and context (document) from your dataset
+
+# Prepare the input text
+input_text = f"question: {question} context: {context}"
+input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)
+
+# Generate the answer
 
 if st.button("Get Answer"):
     if context and question:
         # Generate the answer using the pipeline
-        result = qa_pipeline(question=question, context=context)
-        answer = result['answer']
+        output_ids = model.generate(input_ids)
+        answer = tokenizer.decode(output_ids[0], skip_special_tokens=True)
         st.write("**Answer:**", answer)
     else:
         st.write("Please enter both context and question.")