Upload tokenizer

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: facebook/mbart-large-50-many-to-many-mmt
 tags:
 - generated_from_trainer
+base_model: facebook/mbart-large-50-many-to-many-mmt
 metrics:
 - rouge
 model-index:

special_tokens_map.json

@@ -53,9 +53,27 @@
     "gl_ES",
     "sl_SI"
   ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "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,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -63,7 +81,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cce72faff16b87d24e8f1a908becf0b701e62f44f0ca66daacf0ad8106b7564
-size 17110186
+oid sha256:39a1b1f379379967d4ae65ca4cb40415b6a8e05aa8873159c339d84cd9ddb34f
+size 17094835

tokenizer_config.json

@@ -517,12 +517,19 @@
   "eos_token": "</s>",
   "language_codes": "ML50",
   "mask_token": "<mask>",
+  "max_length": 150,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
   "src_lang": "en_XX",
+  "stride": 0,
   "tgt_lang": null,
   "tokenizer_class": "MBart50Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }