Update app.py

app.py

@@ -7,6 +7,8 @@ import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
+!huggingface-cli login --token "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"
+
 MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
@@ -31,8 +33,7 @@ if not torch.cuda.is_available():
 
 if torch.cuda.is_available():
     model_id = "meta-llama/Llama-2-7b-chat-hf"
-    auth_token = "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"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", use_auth_token=auth_token)
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False