Upload tokenizer

README.md

@@ -1,11 +1,11 @@
 ---
-library_name: transformers
-license: apache-2.0
-datasets:
-- wmt/wmt14
 language:
 - en
 - fr
+license: apache-2.0
+library_name: transformers
+datasets:
+- wmt/wmt14
 metrics:
 - bleu
 pipeline_tag: translation

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -48,10 +48,14 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
+  "max_length": 128,
   "model_max_length": 1024,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "stride": 0,
   "tokenizer_class": "BartTokenizer",
   "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }