fix: remove tokenizer costraint in `gpt2`

lm_eval/models/gpt2.py

@@ -47,27 +47,27 @@ class HFLM(BaseLM):
             revision=revision,
         )
 
-        assert isinstance(
-            self.tokenizer,
-            (
-                transformers.GPT2Tokenizer,
-                transformers.GPT2TokenizerFast,
-                transformers.T5Tokenizer,
-                transformers.T5TokenizerFast,
-            ),
-        ), "this tokenizer has not been checked for compatibility yet!"
+        # assert isinstance(
+        #     self.tokenizer,
+        #     (
+        #         transformers.GPT2Tokenizer,
+        #         transformers.GPT2TokenizerFast,
+        #         transformers.T5Tokenizer,
+        #         transformers.T5TokenizerFast,
+        #     ),
+        # ), "this tokenizer has not been checked for compatibility yet!"
 
         self.vocab_size = self.tokenizer.vocab_size
 
-        if isinstance(
-            self.tokenizer, (transformers.GPT2Tokenizer, transformers.GPT2TokenizerFast)
-        ):
-            assert self.tokenizer.encode("hello\n\nhello") == [
-                31373,
-                198,
-                198,
-                31373,
-            ], self.tokenizer.encode("hello\n\nhello")
+        # if isinstance(
+        #     self.tokenizer, (transformers.GPT2Tokenizer, transformers.GPT2TokenizerFast)
+        # ):
+        #     assert self.tokenizer.encode("hello\n\nhello") == [
+        #         31373,
+        #         198,
+        #         198,
+        #         31373,
+        #     ], self.tokenizer.encode("hello\n\nhello")
 
         # multithreading and batching
         self.batch_size_per_gpu = batch_size  # todo: adaptive batch size