Update app.py

app.py

@@ -5,7 +5,24 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 # Load model and tokenizer
 model_name = "meta-llama/Llama-2-7b-chat-hf"
 print("started loading model")
-model = AutoModelForCausalLM.from_pretrained(model_name)
+
+api_token = "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"  # Replace with your actual API token
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    low_cpu_mem_usage=True,
+    return_dict=True,
+    torch_dtype=torch.float16,
+    revision="main",  # Or the desired revision
+    auth_token=api_token  # Provide the API token here
+)
+
+tokenizer = AutoTokenizer.from_pretrained(
+    model_name,
+    revision="main",  # Or the desired revision
+    auth_token=api_token  # Provide the API token here
+)
+
 print("loaded model")
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 print("loaded tokenizer")