Upload tokenizer

added_tokens.json

@@ -36,5 +36,6 @@
   "                            ": 50260,
   "                             ": 50259,
   "                              ": 50258,
-  "                               ": 50257
+  "                               ": 50257,
+  "[PAD]": 50295
 }

special_tokens_map.json

@@ -13,6 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -353,6 +353,15 @@
       "rstrip": false,
       "normalized": true,
       "special": false
+    },
+    {
+      "id": 50295,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -312,12 +312,21 @@
       "rstrip": false,
       "single_word": false,
       "special": false
+    },
+    "50295": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 2048,
+  "pad_token": "[PAD]",
   "tokenizer_class": "CodeGenTokenizer",
   "unk_token": "<|endoftext|>"
 }