Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 50257
+}

special_tokens_map.json

@@ -1,6 +1,12 @@
 {
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": "<|endoftext|>"
 }

tokenizer.json

@@ -16,6 +16,15 @@
       "rstrip": false,
       "normalized": true,
       "special": true
+    },
+    {
+      "id": 50257,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -8,13 +8,21 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "50257": {
+      "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": 1024,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<pad>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }