Update app.py

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 import os
 from huggingface_hub import InferenceClient
 
-HF_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+
 
 client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta", token=HF_TOKEN)
 
@@ -67,7 +67,23 @@ demo = gr.ChatInterface(
 
 
 
+
+
+
+if __name__ == "__main__":
+    demo.launch()
+
+
+
+
+
+import os
+from transformers import AutoModelForCasualLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
 if not api_token:
+    api_token = os.getenv("HUGGINGFACEHUB_API_TOKEN")
     raise ValueError("❌ ERROR: Hugging Face API token is not set. Please set it as an environment variable.")
 
 # Define model names
@@ -87,8 +103,4 @@ base_model = AutoModelForCausalLM.from_pretrained(
 model = PeftModel.from_pretrained(base_model, peft_model_name, token=api_token)
 
 # Load tokenizer
-tokenizer = AutoTokenizer.from_pretrained(base_model_name, token=api_token)
-
-
-if __name__ == "__main__":
-    demo.launch()
+tokenizer = AutoTokenizer.from_pretrained(base_model_name, token=api_token)