Upload tokenizer

special_tokens_map.json

@@ -1,18 +1,4 @@
 {
-  "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>",
     "lstrip": false,
@@ -20,13 +6,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
   "pad_token": {
     "content": "<pad>",
     "lstrip": false,
@@ -34,13 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer_config.json

@@ -1,14 +1,7 @@
 {
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
       "content": "<pad>",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +9,7 @@
       "single_word": false,
       "special": true
     },
-    "2": {
+    "1": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -24,39 +17,23 @@
       "single_word": false,
       "special": true
     },
-    "3": {
+    "2": {
       "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "46165": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "bos_token": "<s>",
+  "additional_special_tokens": [],
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "max_length": 512,
-  "model_max_length": 8192,
-  "pad_to_multiple_of": null,
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "sep_token": "</s>",
   "sp_model_kwargs": {},
-  "stride": 0,
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
+  "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"
 }