Update app.py

app.py

@@ -7,7 +7,8 @@ import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
-!huggingface-cli login --token "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"
+# !huggingface-cli login --token "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"
+HF_TOKEN = "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"
 
 MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
@@ -33,8 +34,8 @@ if not torch.cuda.is_available():
 
 if torch.cuda.is_available():
     model_id = "meta-llama/Llama-2-7b-chat-hf"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", use_auth_token=HF_TOKEN)
+    tokenizer = AutoTokenizer.from_pretrained(model_id, use_auth_token=HF_TOKEN)
     tokenizer.use_default_system_prompt = False