add tokenizer

added_tokens.json

@@ -1 +1,3 @@
-{"<hl>": 250027}
+{
+  "<hl>": 250027
+}

special_tokens_map.json

@@ -1 +1,18 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<hl>"]}
+{
+  "additional_special_tokens": [
+    "<hl>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3059e2f9b01b617fd5cdb5a0561151e431782bf9a31c660556982db8af7a4890
+oid sha256:a11892dd2e34180882f7d01c5f35400945ce4e3883fd977d42e9ba9d37dbece2
 size 17088356

tokenizer_config.json

@@ -1 +1,23 @@
-{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "src_lang": null, "tgt_lang": null, "additional_special_tokens": null, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "lmqg_output/mbart_large_cc25_dequad/model_ywshaf/epoch_5", "tokenizer_class": "MBartTokenizer"}
+{
+  "additional_special_tokens": null,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "name_or_path": "mbart-large-cc25-dequad",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "MBartTokenizer",
+  "unk_token": "<unk>"
+}