Update app.py

app.py

@@ -1,11 +1,26 @@
-# Use Auto-tokenizer
-
 import streamlit as st
-from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load model and tokenizer
+model_name = "gpt-3.5-turbo"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+def generate_blog_post(topic):
+    prompt = f"Write a detailed blog post about {topic}."
+    inputs = tokenizer.encode(prompt, return_tensors="pt")
+    outputs = model.generate(inputs, max_length=512, num_return_sequences=1)
+    blog_post = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return blog_post
 
-pipe = pipeline('sentiment-analysis')
-text = st.text_area('Enter some text!')
+# Streamlit interface
+st.title("Blog Post Generator")
+st.write("Enter a topic to generate a detailed blog post.")
 
-if text:
-   out = pipe(text)
-   st.json(out)
+topic = st.text_input("Topic", "")
+if st.button("Generate Blog Post"):
+    if topic:
+        blog_post = generate_blog_post(topic)
+        st.write(blog_post)
+    else:
+        st.write("Please enter a topic to generate a blog post.")