Updated app file

app.py

@@ -2,38 +2,29 @@ import streamlit as st
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-# Load your model and tokenizer from Hugging Face
-model_name = "praty7717/Odeyssey"  # Your Hugging Face repo name
+# Load the configuration and model from Hugging Face Hub
+model_name = "praty7717/Odeyssey"  # Use your Hugging Face repo name
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-m = AutoModelForCausalLM.from_pretrained(model_name)
-
-# Function to generate text from a prompt
-def generate_text(model, prompt, max_length=100):
-    input_ids = tokenizer.encode(prompt, return_tensors="pt")
-    
-    # Generate the output
-    with torch.no_grad():
-        output = model.generate(input_ids, max_length=max_length, num_return_sequences=1)
-    
-    # Decode the generated text
-    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
-    return generated_text
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 # Streamlit interface
-st.title("Odeyssey: Poetic Generator")
-st.write("Enter a prompt to generate poetry:")
+st.title("Odeyssey: Poetry Generation")
 
-# Input prompt field
-prompt = st.text_input("Prompt:", value="Once upon a time")  # Default start prompt
+# Prompt input from the user
+start_prompt = st.text_area("Enter your prompt:", "Once upon a time")
 
-# Button to trigger text generation
+# Generate button
 if st.button("Generate"):
-    if prompt:
-        # Generate text using the model
-        generated_text = generate_text(m, prompt, max_length=100)
-        
-        # Display the generated text
-        st.subheader("Generated Text:")
-        st.write(generated_text)
-    else:
-        st.warning("Please enter a prompt.")
+    # Tokenize input
+    input_ids = tokenizer.encode(start_prompt, return_tensors='pt')
+    
+    # Generate text
+    with torch.no_grad():
+        output = model.generate(input_ids, max_length=100, num_return_sequences=1)
+
+    # Decode generated text
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+
+    # Display generated text
+    st.subheader("Generated Text:")
+    st.write(generated_text)