Upload tokenizer

tokenizer.py

@@ -73,7 +73,6 @@ class ProteinTokenizer(PreTrainedTokenizerFast):
             ambiguous_token_ids=ambiguous_token_ids,
             model_input_names=["input_ids", "attention_mask", "special_tokens_mask"],
             tokenizer_object=tokenizer_object,
-            **kwargs,
         )
 
         if other_special_token_ids is not None:

tokenizer_config.json

@@ -69,6 +69,5 @@
   "truncation_side": "right",
   "unk_token": "<unk>",
   "unk_token_id": 1,
-  "vocab_path": "/home/mila/l/lola.lebreton/AMPLIFY/conf/tokenizer/amplify_vocab.txt",
-  "vocab_size": 27
+  "vocab_path": "/home/mila/l/lola.lebreton/AMPLIFY/conf/tokenizer/amplify_vocab.txt"
 }