Upload tokenizer

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
+#version: 0.2
 Ġ t
 Ġ a
 h e

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -82,6 +87,7 @@
     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       "<s>": 0,
       "<pad>": 1,

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_prefix_space": false,
   "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "errors": "replace",
@@ -8,7 +9,6 @@
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "special_tokens_map_file": null,
   "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,
   "unk_token": "<unk>"