Upload tokenizer

special_tokens_map.json

@@ -1,48 +1,34 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
+    "content": "[CLS]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
+    "content": "[MASK]",
+    "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
+    "content": "[PAD]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "</s>",
+    "content": "[SEP]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c46819e8d0adc7ddb668ad06101ea07b41fe6cf590c6acd3072476b3d575426a
-size 17082998
+oid sha256:6c429e3025e4d12e3f578ba24fe6193f43020fd8a24248975cabd00755ca9883
+size 2919460

tokenizer_config.json

@@ -1,62 +1,63 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
-      "content": "<mask>",
-      "lstrip": true,
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "<s>",
+  "cls_token": "[CLS]",
   "do_lower_case": false,
-  "eos_token": "</s>",
   "extra_special_tokens": {},
-  "full_tokenizer_file": null,
-  "mask_token": "<mask>",
-  "max_length": 512,
+  "mask_token": "[MASK]",
+  "max_length": 384,
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "stride": 0,
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 128,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
   "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<unk>"
+  "truncation_strategy": "only_second",
+  "unk_token": "[UNK]"
 }