Upload 5 files

Update tokenizer

special_tokens_map.json

@@ -1,147 +1,753 @@
 {
-    "bos_token": {
-        "content": "<s>",
-        "single_word": false,
-        "lstrip": false,
-        "rstrip": false,
-        "normalized": true
-    },
-    "eos_token": {
-        "content": "</s>",
-        "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": "</s>",
-        "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": "<s>",
-        "single_word": false,
-        "lstrip": false,
-        "rstrip": false,
-        "normalized": true
-    },
-    "mask_token": { "content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-    "additional_special_tokens": [
-        { "content":"<extra_id_99>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_98>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_97>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_96>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_95>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_94>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_93>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_92>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_91>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_90>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_89>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_88>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_87>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_86>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_85>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_84>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_83>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_82>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_81>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_80>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_79>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_78>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_77>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_76>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_75>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_74>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_73>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_72>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_71>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_70>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_69>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_68>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_67>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_66>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_65>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_64>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_63>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_62>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_61>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_60>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_59>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_58>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_57>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_56>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_55>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_54>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_53>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_52>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_51>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_50>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_49>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_48>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_47>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_46>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_45>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_44>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_43>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_42>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_41>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_40>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_39>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_38>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_37>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_36>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_35>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_34>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_33>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_32>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_31>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_30>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_29>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_28>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_27>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_26>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_25>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_24>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_23>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_22>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_21>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_20>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_19>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_18>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_17>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_16>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_15>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_14>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_13>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_12>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_11>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_10>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_9>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_8>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_7>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_6>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_5>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_4>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_3>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_2>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_1>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true },
-        { "content":"<extra_id_0>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true }
-    ]
+  "additional_special_tokens": [
+    {
+      "content": "<extra_id_99>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_98>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_97>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_96>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_95>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_94>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_93>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_92>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_91>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_90>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_89>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_88>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_87>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_86>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_85>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_84>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_83>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_82>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_81>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_80>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_79>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_78>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_77>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_76>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_75>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_74>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_73>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_72>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_71>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_70>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_69>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_68>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_67>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_66>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_65>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_64>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_63>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_62>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_61>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_60>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_59>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_58>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_57>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_56>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_55>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_54>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_53>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_52>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_51>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_50>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_49>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_48>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_47>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_46>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_45>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_44>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_43>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_42>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_41>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_40>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_39>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_38>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_37>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_36>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_35>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_34>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_33>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_32>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_31>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_30>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_29>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_28>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_27>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_26>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_25>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_24>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_23>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_22>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_21>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_20>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_19>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_18>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_17>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_16>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_15>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_14>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_13>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_12>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_11>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_10>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_9>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_8>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_7>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_6>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_5>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_4>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_3>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_2>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_1>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<extra_id_0>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,62 +1,64 @@
 {
-    "errors": "replace",
-    "unk_token": {
-        "content": "<unk>",
-        "single_word": false,
-        "lstrip": false,
-        "rstrip": false,
-        "normalized": true,
-        "__type": "AddedToken"
-    },
-    "bos_token": {
-        "content": "<s>",
-        "single_word": false,
-        "lstrip": false,
-        "rstrip": false,
-        "normalized": true,
-        "__type": "AddedToken"
-    },
-    "eos_token": {
-        "content": "</s>",
-        "single_word": false,
-        "lstrip": false,
-        "rstrip": false,
-        "normalized": true,
-        "__type": "AddedToken"
-    },
-    "add_prefix_space": false,
-    "sep_token": {
-        "content": "</s>",
-        "single_word": false,
-        "lstrip": false,
-        "rstrip": false,
-        "normalized": true,
-        "__type": "AddedToken"
-    },
-    "cls_token": {
-        "content": "<s>",
-        "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"
-    },
-    "model_max_length": 512,
-    "tokenizer_class": "RobertaTokenizer"
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "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,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }