add cpu device to run eval on cpu (#3133)

Summary:

`HFLM` from `lm_eval` can take cpu device. https://github.com/EleutherAI/lm-evaluation-harness/blob/main/lm_eval/models/huggingface.py#L95

Currently running `eval_llama` fails on cpu

Reviewed By: lucylq

Differential Revision: D56313161

Author: cccclai

examples/models/llama2/eval_llama_lib.py

@@ -42,12 +42,11 @@ def __init__(
         tokenizer: Union[SentencePieceTokenizer, Tiktoken],
         max_seq_length: Optional[int] = None,
     ):
-        super().__init__()
+        device = "cuda" if torch.cuda.is_available() else "cpu"
+        super().__init__(device=device)
         self._model = model
         self._tokenizer = tokenizer
-        self._device = (
-            torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
-        )
+        self._device = torch.device(device)
         self._max_seq_length = 2048 if max_seq_length is None else max_seq_length
 
     @property