Upload tokenizer

added_tokens.json

@@ -1,5 +1,4 @@
 {
   "<BOS>": 50257,
-  "<EOS>": 50258,
-  "<PAD>": 50259
+  "<EOS>": 50258
 }

special_tokens_map.json

@@ -13,12 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<PAD>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "<EOS>",
   "unk_token": "<|endoftext|>"
 }

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {
@@ -34,15 +29,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 50259,
-      "content": "<PAD>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -24,21 +24,13 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "50259": {
-      "content": "<PAD>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<BOS>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<EOS>",
   "model_max_length": 1024,
-  "pad_token": "<PAD>",
+  "pad_token": "<EOS>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }