Update app.py

app.py

@@ -13,6 +13,7 @@ from transformers import TextIteratorStreamer
 from threading import Thread
 
 torch.set_num_threads(2)
+HF_TOKEN = os.environ.get("SECRET_TOKEN")      
 
 
 # OBTENER EL DATASET________________________________________________________________________________
@@ -368,8 +369,8 @@ if __name__ == '__main__':
         bnb_4bit_compute_dtype=torch.bfloat16
     )
 
-    tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-    model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", quantization_config=quantization_config, torch_dtype=torch.float16, low_cpu_mem_usage=True)
+    tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it", use_auth_token=HF_TOKEN)
+    model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", quantization_config=quantization_config, torch_dtype=torch.float16, low_cpu_mem_usage=True, use_auth_token=HF_TOKEN)
 
 
     def make_inference(query, hist):