Upload tokenizer with proper BPE files (vocab.json + merges.txt)

special_tokens_map.json

@@ -1,37 +1 @@
-{
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{}

tokenizer_config.json

@@ -1,5 +1,4 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "[MASK]",
@@ -226,17 +225,8 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
   "extra_special_tokens": {},
-  "mask_token": "[MASK]",
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 128000,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "[UNK]"
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }