Create app.py

app.py

@@ -0,0 +1,27 @@
+import streamlit as st
+from transformers import pipeline
+
+# Initialize the text generation pipeline with optimizations
+pipe = pipeline(
+    "text-generation",
+    model="meta-llama/Llama-3.2-1B",
+    device=-1,  # Ensure it runs on CPU
+    use_fast=True,  # Use fast tokenizer
+)
+
+# Streamlit app
+st.title("Llama3.2-1B")
+
+# Text input from the user
+user_input = st.text_input("Enter your message:", "Delete this and write your query?")
+
+# Generate text when the button is clicked
+if st.button("Generate"):
+    messages = [{"role": "user", "content": user_input}]
+    # Reduce max_new_tokens for faster generation
+    output = pipe(messages, max_new_tokens=150)  # Adjust as needed for speed
+    generated_text = output[0]['generated_text']
+    
+    # Display the generated text
+    st.write("Generated Response:")
+    st.write(generated_text)