Upload tokenizer

tokenization_encodon.py

@@ -43,6 +43,7 @@ class EnCodonTokenizer(PreTrainedTokenizer):
         self.codons = self.get_all_codons(seq_type=seq_type)
         self.seq_type = seq_type
         self.special_tokens = [cls_token, sep_token, unk_token, pad_token, mask_token]
+        self.special_tokens = [str(token) for token in self.special_tokens]
 
         self.encoder = {k: i for i, k in enumerate(self.special_tokens + self.codons)}
         self.decoder = {i: k for k, i in self.encoder.items()}