Update app.py

app.py

@@ -1,15 +1,24 @@
 import torch
+import os
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
 
-# ✅ Load your model
+# ✅ Get Hugging Face token from environment variables
+hf_token = os.getenv("HF_TOKEN")  # Automatically retrieves the token from Hugging Face Spaces Secrets
+
+# ✅ Define your model
 model_name = "meta-llama/Llama-3.2-1B-Instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# ✅ Load tokenizer & model with authentication
+print(f"🔄 Loading model: {model_name} ...")
+tokenizer = AutoTokenizer.from_pretrained(model_name, token=hf_token)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     device_map="auto",
-    torch_dtype=torch.float16
+    torch_dtype=torch.float16,
+    token=hf_token
 )
+print(f"✅ Model '{model_name}' loaded successfully!")
 
 # ✅ Define chatbot function
 def chatbot(prompt):
@@ -17,5 +26,6 @@ def chatbot(prompt):
     output = model.generate(**inputs, max_length=200)
     return tokenizer.decode(output[0], skip_special_tokens=True)
 
-# ✅ Deploy on Gradio
+# ✅ Launch Gradio
+print("🚀 Launching chatbot...")
 gr.Interface(fn=chatbot, inputs="text", outputs="text", title="Llama Chatbot").launch()