Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: google/t5-efficient-tiny
 tags:
 - generated_from_trainer
+base_model: google/t5-efficient-tiny
 datasets:
 - generator
 metrics:
@@ -11,8 +11,8 @@ model-index:
 - name: salt_language_ID
   results:
   - task:
-      name: Sequence-to-sequence Language Modeling
       type: text2text-generation
+      name: Sequence-to-sequence Language Modeling
     dataset:
       name: generator
       type: generator
@@ -20,9 +20,9 @@ model-index:
       split: train
       args: default
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.980510752688172
+      name: Accuracy
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

tokenizer.json

@@ -950,8 +950,8 @@
   "pre_tokenizer": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true,
-    "prepend_scheme": "always"
+    "prepend_scheme": "always",
+    "split": true
   },
   "post_processor": {
     "type": "TemplateProcessing",
@@ -1010,8 +1010,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true,
-    "prepend_scheme": "always"
+    "prepend_scheme": "always",
+    "split": true
   },
   "model": {
     "type": "Unigram",