Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: facebook/bart-large
 tags:
 - generated_from_trainer
+base_model: facebook/bart-large
 model-index:
 - name: bart-finetuned-loaf-512-lyrictoplan
   results: []

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<P>": 50265
+}

special_tokens_map.json

@@ -1,25 +1,16 @@
 {
-  "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
-  },
+  "additional_special_tokens": [
+    {
+      "content": "<P>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -28,18 +19,6 @@
     "single_word": false
   },
   "pad_token": "</s>",
-  "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
-  }
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -40,8 +40,19 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "50265": {
+      "content": "<P>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "additional_special_tokens": [
+    "<P>"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
@@ -52,5 +63,6 @@
   "pad_token": "</s>",
   "sep_token": "</s>",
   "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
   "unk_token": "<unk>"
 }