Upload tokenizer

README.md

@@ -1,13 +1,13 @@
 ---
-library_name: transformers
 base_model: bert-base-chinese
-tags:
-- generated_from_trainer
+library_name: transformers
 metrics:
 - accuracy
 - precision
 - recall
 - f1
+tags:
+- generated_from_trainer
 model-index:
 - name: weibo-model-4tags
   results: []

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -41,10 +41,9 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": false,
-  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",