Update app.py

app.py

@@ -1,34 +1,28 @@
-import os
-os.system("pip install transformers~=4.12.3")
 import streamlit as st
-from transformers import GPT2Tokenizer, GPT2Model
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
 
-# Load pre-trained GPT-2 model and tokenizer
-tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
-model = GPT2Model.from_pretrained('gpt2')
+# Load the GPT-2 model and tokenizer
+model_name = "gpt2"
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+model = GPT2LMHeadModel.from_pretrained(model_name)
 
-# Create a text area for the user to input the topic
-topic = st.text_area("Enter a topic to generate a blog post", height=275)
+# Streamlit app layout
+st.title("Blog Post Generator")
+topic = st.text_input("Enter a topic for your blog post:")
 
-# Create sliders for the user to specify the max length, temperature, top-k, and top-p
-max_length = st.sidebar.slider("Max Length", min_value=10, max_value=30)
-temperature = st.sidebar.slider("Temperature", value=1.0, min_value=0.0, max_value=1.0, step=0.05)
-top_k = st.sidebar.slider("Top-k", min_value=0, max_value=5, value=0)
-top_p = st.sidebar.slider("Top-p", min_value=0.0, max_value=1.0, step=0.05, value=0.9)
-num_return_sequences = st.sidebar.number_input('Number of Return Sequences', min_value=1, max_value=5, value=1, step=1)
-
-# Define a function to generate the blog post
-def generate_blogpost(topic):
-    # Encode the topic using the tokenizer
-    encoded_input = tokenizer(topic, return_tensors='pt')
-    
-    # Generate text using the model
-    output = model(**encoded_input)
-    generated_text = tokenizer.decode(output.last_hidden_state[:, 0, :], skip_special_tokens=True)
-    
-    return generated_text
-
-# Create a button to generate the blog post
 if st.button("Generate Blog Post"):
-    generated_text = generate_blogpost(topic)
-    st.write(generated_text)
+    if topic:
+        # Encode the input topic
+        input_ids = tokenizer.encode(topic, return_tensors='pt')
+        
+        # Generate text
+        output = model.generate(input_ids, max_length=500, num_return_sequences=1)
+        
+        # Decode the generated text
+        blog_post = tokenizer.decode(output[0], skip_special_tokens=True)
+        
+        # Display the generated blog post
+        st.subheader("Generated Blog Post:")
+        st.write(blog_post)
+    else:
+        st.warning("Please enter a topic.")