Upload tokenizer

README.md

@@ -1,6 +1,5 @@
 ---
 license: apache-2.0
-base_model: bert-large-uncased
 tags:
 - generated_from_trainer
 datasets:
@@ -10,12 +9,13 @@ metrics:
 - f1
 - precision
 - recall
+base_model: bert-large-uncased
 model-index:
 - name: trainer
   results:
   - task:
-      name: Text Classification
       type: text-classification
+      name: Text Classification
     dataset:
       name: glue
       type: glue
@@ -23,18 +23,18 @@ model-index:
       split: validation
       args: cola
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.8465963566634708
-    - name: F1
-      type: f1
+      name: Accuracy
+    - type: f1
       value: 0.8064540073113251
-    - name: Precision
-      type: precision
+      name: F1
+    - type: precision
       value: 0.840606542828289
-    - name: Recall
-      type: recall
+      name: Precision
+    - type: recall
       value: 0.7876439727431708
+      name: Recall
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}