Upload tokenizer

added_tokens.json

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

special_tokens_map.json

@@ -13,13 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -353,15 +353,6 @@
       "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

@@ -1,4 +1,5 @@
 {
+  "add_eos_token": true,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "50256": {
@@ -312,21 +313,14 @@
       "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]",
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
   "return_token_type_ids": false,
   "tokenizer_class": "CodeGenTokenizer",
   "unk_token": "<|endoftext|>"