add tokenizer

special_tokens_map.json

@@ -1,51 +1 @@
-{
-  "bos_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{"bos_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -1,67 +1 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "__type": "AddedToken",
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "do_lower_case": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 512,
-  "name_or_path": "deberta-large-wnut2017",
-  "pad_token": {
-    "__type": "AddedToken",
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "__type": "AddedToken",
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "special_tokens_map_file": null,
-  "tokenizer_class": "DebertaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "vocab_type": "gpt2"
-}
+{"unk_token": {"content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_bos_token": false, "do_lower_case": false, "model_max_length": 512, "name_or_path": "deberta-large-wnut2017", "special_tokens_map_file": null, "vocab_type": "gpt2", "tokenizer_class": "DebertaTokenizer"}