Update app.py

app.py

@@ -4,23 +4,34 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 from peft import PeftModel, PeftConfig
 from huggingface_hub import login
 
+# Set page config for better display
+st.set_page_config(page_title="LLaMA Chatbot", page_icon="🦙")
+
+# Create a status placeholder
+status_placeholder = st.empty()
+
 # Set your HuggingFace token
-hf_token = st.secrets["HF_TOKEN25"]  # Using Streamlit secrets
+hf_token = st.secrets["HF_TOKEN25"]
 try:
     login(token=hf_token)
-    st.success("Successfully logged in to Hugging Face!")
+    status_placeholder.success("🔑 Successfully logged in to Hugging Face!")
 except Exception as e:
-    st.error(f"Error logging in to Hugging Face: {str(e)}")
+    status_placeholder.error(f"🚫 Error logging in to Hugging Face: {str(e)}")
 
-st.title("LLaMA Chatbot")
+st.title("🦙 LLaMA Chatbot")
 
 @st.cache_resource
 def load_model():
     try:
         model_path = "Alaaeldin/llama2-app"
-        st.info("Loading model... This might take a minute.")
         
+        # Update status for tokenizer loading
+        status_placeholder.info("🔄 Loading tokenizer...")
         tokenizer = AutoTokenizer.from_pretrained(model_path, token=hf_token)
+        status_placeholder.success("✅ Tokenizer loaded successfully!")
+        
+        # Update status for model loading
+        status_placeholder.info("🔄 Loading model... This might take a minute.")
         model = AutoModelForCausalLM.from_pretrained(
             model_path,
             torch_dtype=torch.float16,
@@ -28,10 +39,13 @@ def load_model():
             load_in_8bit=True,
             token=hf_token
         )
-        st.success("✅ Model loaded successfully!")
+        status_placeholder.success("✅ Model loaded successfully!")
+        
+        # Final success message
+        st.success("✨ System is ready! You can now start chatting with the model.")
         return model, tokenizer
     except Exception as e:
-        st.error(f"❌ Error loading model: {str(e)}")
+        status_placeholder.error(f"❌ Error loading model: {str(e)}")
         return None, None
 
 model, tokenizer = load_model()