Fix token authentication method

test_model.py

@@ -1,16 +1,26 @@
+import os
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
+from huggingface_hub import login
 
 def generate_response(question):
     try:
-        # Load tokenizer
-        tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf")
-        tokenizer.pad_token = tokenizer.eos_token
+        # Debug print to verify token
+        token = os.environ.get('HUGGINGFACE_TOKEN')
+        print(f"Token available: {'Yes' if token else 'No'}")
+        login(token)
         
-        # Load base model and apply LoRA weights
+        print("Loading tokenizer...")
+        tokenizer = AutoTokenizer.from_pretrained(
+            "meta-llama/Llama-2-7b-hf",
+            use_auth_token=True  # Changed to use environment token
+        )
+        
+        print("Loading model...")
         base_model = AutoModelForCausalLM.from_pretrained(
             "meta-llama/Llama-2-7b-hf",
+            use_auth_token=True,  # Changed to use environment token
             load_in_8bit=True,
             device_map="auto"
         )