Update app.py

app.py

@@ -1,61 +1,27 @@
 import streamlit as st
-from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Load model and tokenizer
-model_name = "gpt2-large"  # You can change this to a larger GPT model if needed
+model_name = "gpt2"  # You can also try other models like "gpt2-medium", "gpt2-large", etc.
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 
-# Set up zero-shot classification pipeline
-classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
-
-# Function to generate blog post
-def generate_blog_post(topic, max_length=500):
-    prompt = f"Write a blog post about {topic}:\n\n"
-    inputs = tokenizer(prompt, return_tensors="pt")
-    
-    outputs = model.generate(
-        inputs.input_ids,
-        max_length=max_length,
-        num_return_sequences=1,
-        no_repeat_ngram_size=2,
-        top_k=50,
-        top_p=0.95,
-        temperature=0.7,
-    )
-    
-    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return generated_text.replace(prompt, "")
-
-# Function to classify blog post
-def classify_blog_post(text, labels):
-    result = classifier(text, labels)
-    return result
+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, pad_token_id=tokenizer.eos_token_id)
+    blog_post = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return blog_post
 
 # Streamlit interface
 st.title("Blog Post Generator")
-
-topic = st.text_input("Enter a topic for your blog post:")
-generate_button = st.button("Generate Blog Post")
-
-if generate_button and topic:
-    with st.spinner("Generating blog post..."):
-        blog_post = generate_blog_post(topic)
-        
-        # Display the generated blog post
-        st.subheader("Generated Blog Post")
-        st.text_area("Blog Content", blog_post, height=300)
-        
-        # Classify the generated blog post
-        st.subheader("Blog Post Classification")
-        labels = ["Technology", "Travel", "Food", "Health", "Finance"]
-        classification = classify_blog_post(blog_post, labels)
-        
-        for label, score in zip(classification['labels'], classification['scores']):
-            st.write(f"{label}: {score:.2f}")
-
-st.sidebar.title("About")
-st.sidebar.info(
-    "This app generates a blog post on a given topic using a large GPT model. "
-    "It also classifies the generated post using zero-shot classification."
-)
+st.write("Enter a topic to generate a detailed blog post.")
+
+topic = st.text_input("Topic", "")
+if st.button("Generate Blog Post"):
+    if topic:
+        with st.spinner('Generating blog post...'):
+            blog_post = generate_blog_post(topic)
+        st.write(blog_post)
+    else:
+        st.write("Please enter a topic to generate a blog post.")