Update app.py

app.py

@@ -1,9 +1,36 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import streamlit as st
-from transformers import pipeline
 
-pipe = pipeline('sentiment-analysis')
-text = st.text_area('Enter some text!')
+# Load the tokenizer and model using auto tokenizer and auto model
+tokenizer = AutoTokenizer.from_pretrained('gpt2-large')
+model = AutoModelForCausalLM.from_pretrained('gpt2-large')
 
-if text:
-    out = pipe(text)
-    st.json(out)
+def generate_blog_post(topic):
+    prompt = f"Write a blog post about {topic}."
+    inputs = tokenizer.encode(prompt, return_tensors='pt')
+    
+    # Generate text
+    outputs = model.generate(inputs, max_length=500, num_return_sequences=1, do_sample=True, top_p=0.95, top_k=60)
+    
+    # Decode the generated text
+    text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return text
+
+# Streamlit interface
+st.title("Blog Post Generator")
+st.write("Generate a blog post for a given topic using GPT-2 Large.")
+
+topic = st.text_input("Enter the topic for the blog post:")
+
+if st.button("Generate Blog Post"):
+    if topic:
+        with st.spinner("Generating..."):
+            try:
+                blog_post = generate_blog_post(topic)
+                st.subheader("Generated Blog Post")
+                st.write(blog_post)
+            except Exception as e:
+                st.error(f"Error generating blog post: {e}")
+    else:
+        st.warning("Please enter a topic.")